< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 7 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.6197. Min Act: -0.1700

Data Index: 8127357 (Open Web Text)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.4947. Min Act: -0.1700

Data Index: 6262446 (Open Web Text)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.4947. Min Act: -0.1700

Data Index: 1099211 (Open Web Text)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.4322. Min Act: -0.1700

Data Index: 5416382 (Open Web Text)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.4322. Min Act: -0.1700

Data Index: 4690155 (Open Web Text)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.4322. Min Act: -0.1700

Data Index: 2926366 (Open Web Text)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.4322. Min Act: -0.1700

Data Index: 2069669 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.4010. Min Act: -0.1700

Data Index: 8275059 (Open Web Text)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.4010. Min Act: -0.1700

Data Index: 5054962 (Open Web Text)

Max Activating Token Index: 712

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.4322. Min Act: -0.1700

Data Index: 7929666 (Open Web Text)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.4010. Min Act: -0.1700

Data Index: 3362525 (Open Web Text)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.3697. Min Act: -0.1700

Data Index: 6269962 (Open Web Text)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.3697. Min Act: -0.1700

Data Index: 7510339 (Open Web Text)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.3697. Min Act: -0.1700

Data Index: 5871957 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.3697. Min Act: -0.1700

Data Index: 8633905 (Open Web Text)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.3697. Min Act: -0.1700

Data Index: 827885 (Open Web Text)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.3385. Min Act: -0.1700

Data Index: 2633794 (Open Web Text)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.3072. Min Act: -0.1700

Data Index: 7759083 (Open Web Text)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.3385. Min Act: -0.1700

Data Index: 1959780 (Open Web Text)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.6197. Min Range: -5.6197

Max Act: 5.3385. Min Act: -0.1700

Data Index: 17627 (Open Web Text)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #19