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

Dataset: Open Web Text

Neuron 372 in Layer 5

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: 5.4564. Min Range: -5.4564

Max Act: 5.4564. Min Act: -0.1700

Data Index: 1059085 (Open Web Text)

Max Activating Token Index: 444

Text #1

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3858. Min Act: -0.1700

Data Index: 3087932 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3533. Min Act: -0.1700

Data Index: 1059095 (Open Web Text)

Max Activating Token Index: 451

Text #3

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3539. Min Act: -0.1700

Data Index: 3087919 (Open Web Text)

Max Activating Token Index: 916

Text #4

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3714. Min Act: -0.1700

Data Index: 3087930 (Open Web Text)

Max Activating Token Index: 363

Text #5

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3611. Min Act: -0.1700

Data Index: 3087926 (Open Web Text)

Max Activating Token Index: 362

Text #6

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3292. Min Act: -0.1700

Data Index: 7008807 (Open Web Text)

Max Activating Token Index: 468

Text #7

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3562. Min Act: -0.1700

Data Index: 7008811 (Open Web Text)

Max Activating Token Index: 468

Text #8

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3515. Min Act: -0.1700

Data Index: 7008799 (Open Web Text)

Max Activating Token Index: 365

Text #9

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3169. Min Act: -0.1700

Data Index: 1059090 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3346. Min Act: -0.1700

Data Index: 3087935 (Open Web Text)

Max Activating Token Index: 804

Text #11

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3167. Min Act: -0.1700

Data Index: 7008833 (Open Web Text)

Max Activating Token Index: 875

Text #12

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3125. Min Act: -0.1700

Data Index: 7008830 (Open Web Text)

Max Activating Token Index: 489

Text #13

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3451. Min Act: -0.1700

Data Index: 3087924 (Open Web Text)

Max Activating Token Index: 465

Text #14

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.2874. Min Act: -0.1700

Data Index: 3087938 (Open Web Text)

Max Activating Token Index: 449

Text #15

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3113. Min Act: -0.1700

Data Index: 3087937 (Open Web Text)

Max Activating Token Index: 498

Text #16

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.2973. Min Act: -0.1700

Data Index: 7008823 (Open Web Text)

Max Activating Token Index: 955

Text #17

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3024. Min Act: -0.1700

Data Index: 1059078 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.3028. Min Act: -0.1700

Data Index: 7008806 (Open Web Text)

Max Activating Token Index: 429

Text #19

Max Range: 5.4564. Min Range: -5.4564

Max Act: 5.2657. Min Act: -0.1700

Data Index: 7008798 (Open Web Text)

Max Activating Token Index: 643