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

Dataset: Open Web Text

Neuron 2035 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: 3.2913. Min Range: -3.2913

Max Act: 3.2913. Min Act: -0.1700

Data Index: 1861919 (Open Web Text)

Max Activating Token Index: 842

Text #1

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2723. Min Act: -0.1700

Data Index: 951603 (Open Web Text)

Max Activating Token Index: 263

Text #2

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2423. Min Act: -0.1700

Data Index: 903337 (Open Web Text)

Max Activating Token Index: 424

Text #3

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2253. Min Act: -0.1700

Data Index: 8066021 (Open Web Text)

Max Activating Token Index: 42

Text #4

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2311. Min Act: -0.1700

Data Index: 7638335 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2088. Min Act: -0.1700

Data Index: 69744 (Open Web Text)

Max Activating Token Index: 403

Text #6

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1938. Min Act: -0.1700

Data Index: 4578211 (Open Web Text)

Max Activating Token Index: 568

Text #7

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1742. Min Act: -0.1700

Data Index: 723470 (Open Web Text)

Max Activating Token Index: 701

Text #8

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1583. Min Act: -0.1700

Data Index: 183899 (Open Web Text)

Max Activating Token Index: 745

Text #9

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1443. Min Act: -0.1700

Data Index: 3673648 (Open Web Text)

Max Activating Token Index: 805

Text #10

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1417. Min Act: -0.1700

Data Index: 2056826 (Open Web Text)

Max Activating Token Index: 827

Text #11

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1497. Min Act: -0.1700

Data Index: 6033589 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1095. Min Act: -0.1700

Data Index: 2635440 (Open Web Text)

Max Activating Token Index: 863

Text #13

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1302. Min Act: -0.1700

Data Index: 8301113 (Open Web Text)

Max Activating Token Index: 165

Text #14

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1325. Min Act: -0.1700

Data Index: 8642473 (Open Web Text)

Max Activating Token Index: 790

Text #15

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1311. Min Act: -0.1700

Data Index: 7166723 (Open Web Text)

Max Activating Token Index: 940

Text #16

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1179. Min Act: -0.1700

Data Index: 6223647 (Open Web Text)

Max Activating Token Index: 533

Text #17

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1498. Min Act: -0.1700

Data Index: 5421212 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1192. Min Act: -0.1700

Data Index: 810012 (Open Web Text)

Max Activating Token Index: 183

Text #19

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1221. Min Act: -0.1700

Data Index: 7706319 (Open Web Text)

Max Activating Token Index: 123