< Prev | Home | Model | Random | Next >

Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 14 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')



Text #0

Max Range: 12.7655. Min Range: -12.7655

Max Act: 12.7655. Min Act: -0.1700

Data Index: 3874402 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 12.7655. Min Range: -12.7655

Max Act: 12.2655. Min Act: -0.1700

Data Index: 3874399 (Open Web Text)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 12.7655. Min Range: -12.7655

Max Act: 12.2030. Min Act: -0.1700

Data Index: 3874403 (Open Web Text)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 12.7655. Min Range: -12.7655

Max Act: 12.0155. Min Act: -0.1700

Data Index: 7454580 (Open Web Text)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 12.7655. Min Range: -12.7655

Max Act: 11.6405. Min Act: -0.1700

Data Index: 4683521 (Open Web Text)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 12.7655. Min Range: -12.7655

Max Act: 11.6405. Min Act: -0.1700

Data Index: 3874396 (Open Web Text)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 12.7655. Min Range: -12.7655

Max Act: 11.3280. Min Act: -0.1700

Data Index: 3874397 (Open Web Text)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 12.7655. Min Range: -12.7655

Max Act: 11.3280. Min Act: -0.1700

Data Index: 3874394 (Open Web Text)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 12.7655. Min Range: -12.7655

Max Act: 11.3280. Min Act: -0.1700

Data Index: 3874400 (Open Web Text)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 12.7655. Min Range: -12.7655

Max Act: 11.3280. Min Act: -0.1700

Data Index: 6248933 (Open Web Text)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 12.7655. Min Range: -12.7655

Max Act: 10.9530. Min Act: -0.1700

Data Index: 4683515 (Open Web Text)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 12.7655. Min Range: -12.7655

Max Act: 11.0155. Min Act: -0.1700

Data Index: 3874395 (Open Web Text)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 12.7655. Min Range: -12.7655

Max Act: 11.0155. Min Act: -0.1700

Data Index: 2165730 (Open Web Text)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 12.7655. Min Range: -12.7655

Max Act: 10.8905. Min Act: -0.1700

Data Index: 7139219 (Open Web Text)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 12.7655. Min Range: -12.7655

Max Act: 10.8280. Min Act: -0.1700

Data Index: 5319654 (Open Web Text)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 12.7655. Min Range: -12.7655

Max Act: 10.7655. Min Act: -0.1700

Data Index: 3874398 (Open Web Text)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 12.7655. Min Range: -12.7655

Max Act: 10.7030. Min Act: -0.1700

Data Index: 2060127 (Open Web Text)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 12.7655. Min Range: -12.7655

Max Act: 10.6405. Min Act: -0.1700

Data Index: 3427128 (Open Web Text)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 12.7655. Min Range: -12.7655

Max Act: 10.7030. Min Act: -0.1700

Data Index: 4683520 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 12.7655. Min Range: -12.7655

Max Act: 10.5155. Min Act: -0.1700

Data Index: 4683517 (Open Web Text)

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #19