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

Dataset: Open Web Text

Neuron 731 in Layer 6

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: 4.9569. Min Range: -4.9569

Max Act: 4.9569. Min Act: -0.1700

Data Index: 3347694 (Open Web Text)

Max Activating Token Index: 502

Text #1

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.9314. Min Act: -0.1700

Data Index: 823794 (Open Web Text)

Max Activating Token Index: 592

Text #2

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.8603. Min Act: -0.1700

Data Index: 6722029 (Open Web Text)

Max Activating Token Index: 621

Text #3

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.8562. Min Act: -0.1700

Data Index: 1382151 (Open Web Text)

Max Activating Token Index: 267

Text #4

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.8586. Min Act: -0.1700

Data Index: 8586684 (Open Web Text)

Max Activating Token Index: 280

Text #5

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.8165. Min Act: -0.1700

Data Index: 3221762 (Open Web Text)

Max Activating Token Index: 156

Text #6

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.8190. Min Act: -0.1700

Data Index: 2647988 (Open Web Text)

Max Activating Token Index: 221

Text #7

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.7493. Min Act: -0.1700

Data Index: 8248234 (Open Web Text)

Max Activating Token Index: 626

Text #8

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.7495. Min Act: -0.1700

Data Index: 7738659 (Open Web Text)

Max Activating Token Index: 938

Text #9

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.6982. Min Act: -0.1700

Data Index: 3357909 (Open Web Text)

Max Activating Token Index: 789

Text #10

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.6545. Min Act: -0.1700

Data Index: 7925762 (Open Web Text)

Max Activating Token Index: 411

Text #11

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.6793. Min Act: -0.1700

Data Index: 8249288 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.6589. Min Act: -0.1700

Data Index: 5711602 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.6585. Min Act: -0.1700

Data Index: 3930066 (Open Web Text)

Max Activating Token Index: 801

Text #14

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.6317. Min Act: -0.1700

Data Index: 7142260 (Open Web Text)

Max Activating Token Index: 893

Text #15

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.6265. Min Act: -0.1700

Data Index: 5651189 (Open Web Text)

Max Activating Token Index: 155

Text #16

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.6062. Min Act: -0.1700

Data Index: 7542967 (Open Web Text)

Max Activating Token Index: 63

Text #17

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.5709. Min Act: -0.1700

Data Index: 4565486 (Open Web Text)

Max Activating Token Index: 240

Text #18

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.5842. Min Act: -0.1700

Data Index: 6281711 (Open Web Text)

Max Activating Token Index: 897

Text #19

Max Range: 4.9569. Min Range: -4.9569

Max Act: 4.6224. Min Act: -0.1700

Data Index: 5025261 (Open Web Text)

Max Activating Token Index: 363