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

Dataset: Open Web Text

Neuron 1128 in Layer 4

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: 5.8518. Min Range: -5.8518

Max Act: 5.7834. Min Act: -0.1700

Data Index: 6812887 (Open Web Text)

Max Activating Token Index: 560

Text #1

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.8124. Min Act: -0.1700

Data Index: 5538426 (Open Web Text)

Max Activating Token Index: 465

Text #2

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.8518. Min Act: -0.1700

Data Index: 7482149 (Open Web Text)

Max Activating Token Index: 505

Text #3

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.7821. Min Act: -0.1700

Data Index: 5020420 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.7538. Min Act: -0.1700

Data Index: 3452409 (Open Web Text)

Max Activating Token Index: 811

Text #5

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.7718. Min Act: -0.1700

Data Index: 1032422 (Open Web Text)

Max Activating Token Index: 582

Text #6

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.7178. Min Act: -0.1700

Data Index: 1096645 (Open Web Text)

Max Activating Token Index: 533

Text #7

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.7611. Min Act: -0.1700

Data Index: 6786867 (Open Web Text)

Max Activating Token Index: 667

Text #8

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.7006. Min Act: -0.1700

Data Index: 7882834 (Open Web Text)

Max Activating Token Index: 530

Text #9

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.7112. Min Act: -0.1700

Data Index: 7855579 (Open Web Text)

Max Activating Token Index: 756

Text #10

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.7279. Min Act: -0.1700

Data Index: 3416612 (Open Web Text)

Max Activating Token Index: 397

Text #11

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.6779. Min Act: -0.1700

Data Index: 4842921 (Open Web Text)

Max Activating Token Index: 469

Text #12

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.6986. Min Act: -0.1700

Data Index: 8367772 (Open Web Text)

Max Activating Token Index: 1007

Text #13

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.6693. Min Act: -0.1700

Data Index: 8390907 (Open Web Text)

Max Activating Token Index: 147

Text #14

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.6654. Min Act: -0.1700

Data Index: 8487263 (Open Web Text)

Max Activating Token Index: 552

Text #15

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.6438. Min Act: -0.1700

Data Index: 5038909 (Open Web Text)

Max Activating Token Index: 571

Text #16

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.6271. Min Act: -0.1700

Data Index: 2328881 (Open Web Text)

Max Activating Token Index: 311

Text #17

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.7158. Min Act: -0.1700

Data Index: 4914784 (Open Web Text)

Max Activating Token Index: 588

Text #18

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.7169. Min Act: -0.1700

Data Index: 606377 (Open Web Text)

Max Activating Token Index: 838

Text #19

Max Range: 5.8518. Min Range: -5.8518

Max Act: 5.6325. Min Act: -0.1700

Data Index: 6412 (Open Web Text)

Max Activating Token Index: 343