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

Dataset: Open Web Text

Neuron 2016 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: 1.1477. Min Range: -1.1477

Max Act: 1.1477. Min Act: -0.1700

Data Index: 3980442 (Open Web Text)

Max Activating Token Index: 66

Text #1

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1426. Min Act: -0.1700

Data Index: 8232469 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1383. Min Act: -0.1700

Data Index: 6083446 (Open Web Text)

Max Activating Token Index: 112

Text #3

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1386. Min Act: -0.1700

Data Index: 7548827 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1362. Min Act: -0.1700

Data Index: 6241450 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1297. Min Act: -0.1700

Data Index: 8304920 (Open Web Text)

Max Activating Token Index: 119

Text #6

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1354. Min Act: -0.1700

Data Index: 3540430 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1365. Min Act: -0.1700

Data Index: 3785379 (Open Web Text)

Max Activating Token Index: 116

Text #8

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1254. Min Act: -0.1700

Data Index: 8671990 (Open Web Text)

Max Activating Token Index: 166

Text #9

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1244. Min Act: -0.1700

Data Index: 3601113 (Open Web Text)

Max Activating Token Index: 247

Text #10

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1305. Min Act: -0.1700

Data Index: 4430431 (Open Web Text)

Max Activating Token Index: 248

Text #11

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1241. Min Act: -0.1700

Data Index: 3200022 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1222. Min Act: -0.1700

Data Index: 4138456 (Open Web Text)

Max Activating Token Index: 164

Text #13

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1116. Min Act: -0.1700

Data Index: 6149682 (Open Web Text)

Max Activating Token Index: 39

Text #14

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1082. Min Act: -0.1700

Data Index: 3271058 (Open Web Text)

Max Activating Token Index: 164

Text #15

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1090. Min Act: -0.1700

Data Index: 4231050 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1041. Min Act: -0.1700

Data Index: 3174382 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1020. Min Act: -0.1700

Data Index: 7982601 (Open Web Text)

Max Activating Token Index: 25

Text #18

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1076. Min Act: -0.1700

Data Index: 5284978 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1042. Min Act: -0.1700

Data Index: 6129387 (Open Web Text)

Max Activating Token Index: 308