Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 880 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.1844. Min Act: -0.1700

Data Index: 5029996 (Open Web Text)

Max Activating Token Index: 410

Text #1

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.1766. Min Act: -0.1700

Data Index: 3610005 (Open Web Text)

Max Activating Token Index: 357

Text #2

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0049. Min Act: -0.1700

Data Index: 1953283 (Open Web Text)

Max Activating Token Index: 879

Text #3

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.9733. Min Act: -0.1700

Data Index: 478788 (Open Web Text)

Max Activating Token Index: 414

Text #4

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.9814. Min Act: -0.1700

Data Index: 7496219 (Open Web Text)

Max Activating Token Index: 924

Text #5

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.9648. Min Act: -0.1700

Data Index: 699508 (Open Web Text)

Max Activating Token Index: 409

Text #6

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.9147. Min Act: -0.1700

Data Index: 7601094 (Open Web Text)

Max Activating Token Index: 94

Text #7

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.8857. Min Act: -0.1700

Data Index: 7646966 (Open Web Text)

Max Activating Token Index: 998

Text #8

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.8350. Min Act: -0.1700

Data Index: 6711199 (Open Web Text)

Max Activating Token Index: 842

Text #9

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.8393. Min Act: -0.1700

Data Index: 4506617 (Open Web Text)

Max Activating Token Index: 541

Text #10

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.8097. Min Act: -0.1700

Data Index: 3947730 (Open Web Text)

Max Activating Token Index: 36

Text #11

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.8055. Min Act: -0.1700

Data Index: 4206669 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.7955. Min Act: -0.1700

Data Index: 2441550 (Open Web Text)

Max Activating Token Index: 307

Text #13

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.7728. Min Act: -0.1700

Data Index: 5118301 (Open Web Text)

Max Activating Token Index: 688

Text #14

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.7559. Min Act: -0.1700

Data Index: 6627191 (Open Web Text)

Max Activating Token Index: 841

Text #15

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.7734. Min Act: -0.1700

Data Index: 6624218 (Open Web Text)

Max Activating Token Index: 813

Text #16

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.7379. Min Act: -0.1700

Data Index: 16703 (Open Web Text)

Max Activating Token Index: 745

Text #17

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.7488. Min Act: -0.1700

Data Index: 1166884 (Open Web Text)

Max Activating Token Index: 614

Text #18

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.7264. Min Act: -0.1700

Data Index: 1624370 (Open Web Text)

Max Activating Token Index: 431

Text #19

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.7576. Min Act: -0.1700

Data Index: 5776359 (Open Web Text)

Max Activating Token Index: 10