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

Dataset: Open Web Text

Neuron 56 in Layer 3

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: 3.7452. Min Range: -3.7452

Max Act: 3.7452. Min Act: -0.1700

Data Index: 8609347 (Open Web Text)

Max Activating Token Index: 472

Text #1

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.7250. Min Act: -0.1700

Data Index: 3689216 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.6862. Min Act: -0.1700

Data Index: 5062674 (Open Web Text)

Max Activating Token Index: 607

Text #3

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.6596. Min Act: -0.1700

Data Index: 8711150 (Open Web Text)

Max Activating Token Index: 830

Text #4

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.6204. Min Act: -0.1700

Data Index: 1249662 (Open Web Text)

Max Activating Token Index: 433

Text #5

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5934. Min Act: -0.1700

Data Index: 3111635 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5695. Min Act: -0.1700

Data Index: 5973174 (Open Web Text)

Max Activating Token Index: 746

Text #7

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4842. Min Act: -0.1700

Data Index: 1962987 (Open Web Text)

Max Activating Token Index: 506

Text #8

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5109. Min Act: -0.1700

Data Index: 7380050 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5143. Min Act: -0.1700

Data Index: 4213117 (Open Web Text)

Max Activating Token Index: 767

Text #10

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.5251. Min Act: -0.1700

Data Index: 46048 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4865. Min Act: -0.1700

Data Index: 5185729 (Open Web Text)

Max Activating Token Index: 561

Text #12

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4631. Min Act: -0.1700

Data Index: 571850 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4966. Min Act: -0.1700

Data Index: 7384959 (Open Web Text)

Max Activating Token Index: 1006

Text #14

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4449. Min Act: -0.1700

Data Index: 1651208 (Open Web Text)

Max Activating Token Index: 689

Text #15

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4638. Min Act: -0.1700

Data Index: 6368947 (Open Web Text)

Max Activating Token Index: 53

Text #16

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4425. Min Act: -0.1700

Data Index: 2057814 (Open Web Text)

Max Activating Token Index: 642

Text #17

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4755. Min Act: -0.1700

Data Index: 906611 (Open Web Text)

Max Activating Token Index: 810

Text #18

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4685. Min Act: -0.1700

Data Index: 3318801 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 3.7452. Min Range: -3.7452

Max Act: 3.4421. Min Act: -0.1700

Data Index: 6040378 (Open Web Text)

Max Activating Token Index: 819