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

Dataset: Open Web Text

Neuron 2182 in Layer 0

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: 0.8283. Min Range: -0.8283

Max Act: 0.8283. Min Act: -0.1700

Data Index: 7251932 (Open Web Text)

Max Activating Token Index: 161

Text #1

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7539. Min Act: -0.1700

Data Index: 7347390 (Open Web Text)

Max Activating Token Index: 104

Text #2

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7542. Min Act: -0.1698

Data Index: 610439 (Open Web Text)

Max Activating Token Index: 94

Text #3

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7488. Min Act: -0.1696

Data Index: 1626148 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7361. Min Act: -0.1698

Data Index: 1379628 (Open Web Text)

Max Activating Token Index: 90

Text #5

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7404. Min Act: -0.1700

Data Index: 4023834 (Open Web Text)

Max Activating Token Index: 99

Text #6

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7351. Min Act: -0.1700

Data Index: 2527700 (Open Web Text)

Max Activating Token Index: 129

Text #7

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7335. Min Act: -0.1700

Data Index: 1629210 (Open Web Text)

Max Activating Token Index: 102

Text #8

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7344. Min Act: -0.1700

Data Index: 2614023 (Open Web Text)

Max Activating Token Index: 87

Text #9

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7362. Min Act: -0.1700

Data Index: 7142996 (Open Web Text)

Max Activating Token Index: 88

Text #10

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7325. Min Act: -0.1700

Data Index: 5603214 (Open Web Text)

Max Activating Token Index: 101

Text #11

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7328. Min Act: -0.1699

Data Index: 8473466 (Open Web Text)

Max Activating Token Index: 137

Text #12

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7247. Min Act: -0.1695

Data Index: 5823898 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7291. Min Act: -0.1696

Data Index: 3342010 (Open Web Text)

Max Activating Token Index: 88

Text #14

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7297. Min Act: -0.1699

Data Index: 8407631 (Open Web Text)

Max Activating Token Index: 98

Text #15

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7210. Min Act: -0.1700

Data Index: 5881130 (Open Web Text)

Max Activating Token Index: 90

Text #16

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7226. Min Act: -0.1699

Data Index: 7114677 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7246. Min Act: -0.1700

Data Index: 1765417 (Open Web Text)

Max Activating Token Index: 100

Text #18

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7193. Min Act: -0.1694

Data Index: 4801484 (Open Web Text)

Max Activating Token Index: 104

Text #19

Max Range: 0.8283. Min Range: -0.8283

Max Act: 0.7254. Min Act: -0.1700

Data Index: 29863 (Open Web Text)

Max Activating Token Index: 87