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

Dataset: Open Web Text

Neuron 459 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: 3.3338. Min Range: -3.3338

Max Act: 3.3338. Min Act: -0.1700

Data Index: 7444432 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.3025. Min Act: -0.1700

Data Index: 5537217 (Open Web Text)

Max Activating Token Index: 958

Text #2

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2450. Min Act: -0.1700

Data Index: 6262721 (Open Web Text)

Max Activating Token Index: 850

Text #3

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2695. Min Act: -0.1700

Data Index: 6928804 (Open Web Text)

Max Activating Token Index: 70

Text #4

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2026. Min Act: -0.1700

Data Index: 3378970 (Open Web Text)

Max Activating Token Index: 303

Text #5

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2168. Min Act: -0.1700

Data Index: 6223567 (Open Web Text)

Max Activating Token Index: 519

Text #6

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.2136. Min Act: -0.1700

Data Index: 8496126 (Open Web Text)

Max Activating Token Index: 677

Text #7

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1657. Min Act: -0.1700

Data Index: 6994353 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1752. Min Act: -0.1700

Data Index: 3753211 (Open Web Text)

Max Activating Token Index: 746

Text #9

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1627. Min Act: -0.1700

Data Index: 1951948 (Open Web Text)

Max Activating Token Index: 422

Text #10

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1435. Min Act: -0.1700

Data Index: 6001152 (Open Web Text)

Max Activating Token Index: 720

Text #11

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1546. Min Act: -0.1700

Data Index: 6961438 (Open Web Text)

Max Activating Token Index: 902

Text #12

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1359. Min Act: -0.1700

Data Index: 5314653 (Open Web Text)

Max Activating Token Index: 842

Text #13

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1504. Min Act: -0.1700

Data Index: 576063 (Open Web Text)

Max Activating Token Index: 935

Text #14

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1390. Min Act: -0.1700

Data Index: 2354751 (Open Web Text)

Max Activating Token Index: 277

Text #15

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1480. Min Act: -0.1700

Data Index: 4829884 (Open Web Text)

Max Activating Token Index: 984

Text #16

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1176. Min Act: -0.1700

Data Index: 3696079 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1064. Min Act: -0.1700

Data Index: 5793265 (Open Web Text)

Max Activating Token Index: 882

Text #18

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1248. Min Act: -0.1700

Data Index: 1779139 (Open Web Text)

Max Activating Token Index: 972

Text #19

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.1072. Min Act: -0.1700

Data Index: 6105914 (Open Web Text)

Max Activating Token Index: 250