< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6346 in Layer 39

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.3692. Min Act: -0.1700

Data Index: 6959013 (Open Web Text)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.3067. Min Act: -0.1700

Data Index: 6262321 (Open Web Text)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.3067. Min Act: -0.1700

Data Index: 2203741 (Open Web Text)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.2754. Min Act: -0.1700

Data Index: 8765591 (Open Web Text)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.2754. Min Act: -0.1700

Data Index: 6100847 (Open Web Text)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.2129. Min Act: -0.1700

Data Index: 2210397 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.1817. Min Act: -0.1700

Data Index: 6156442 (Open Web Text)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.1504. Min Act: -0.1700

Data Index: 8797107 (Open Web Text)

Max Activating Token Index: 291

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.1504. Min Act: -0.1700

Data Index: 3906347 (Open Web Text)

Max Activating Token Index: 466

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.1192. Min Act: -0.1700

Data Index: 8369820 (Open Web Text)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.1192. Min Act: -0.1700

Data Index: 6617771 (Open Web Text)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.0879. Min Act: -0.1700

Data Index: 8772256 (Open Web Text)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.0879. Min Act: -0.1700

Data Index: 7294242 (Open Web Text)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.0567. Min Act: -0.1700

Data Index: 2363219 (Open Web Text)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.0879. Min Act: -0.1700

Data Index: 8623599 (Open Web Text)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.0254. Min Act: -0.1700

Data Index: 3118773 (Open Web Text)

Max Activating Token Index: 938

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.0254. Min Act: -0.1700

Data Index: 4682599 (Open Web Text)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.0567. Min Act: -0.1700

Data Index: 334944 (Open Web Text)

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.0567. Min Act: -0.1700

Data Index: 2560005 (Open Web Text)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.0567. Min Act: -0.1700

Data Index: 45382 (Open Web Text)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #19