Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1603 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.9352. Min Act: -0.1700

Data Index: 41421 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.7162. Min Act: -0.1700

Data Index: 536404 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1061523 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.6223. Min Act: -0.1700

Data Index: 714085 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5910. Min Act: -0.1700

Data Index: 1061952 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.6223. Min Act: -0.1700

Data Index: 870293 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5597. Min Act: -0.1700

Data Index: 1002162 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5910. Min Act: -0.1700

Data Index: 1171160 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.4657. Min Act: -0.1700

Data Index: 645 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5284. Min Act: -0.1700

Data Index: 883291 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5284. Min Act: -0.1700

Data Index: 116761 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.4970. Min Act: -0.1700

Data Index: 1314733 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5284. Min Act: -0.1700

Data Index: 349922 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.4970. Min Act: -0.1700

Data Index: 404525 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5284. Min Act: -0.1700

Data Index: 981089 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.4970. Min Act: -0.1700

Data Index: 1021043 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.4970. Min Act: -0.1699

Data Index: 1354930 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.4970. Min Act: -0.1700

Data Index: 172288 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.5284. Min Act: -0.1700

Data Index: 861340 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 3.9352. Min Range: -3.9352

Max Act: 3.4657. Min Act: -0.1700

Data Index: 653417 (C4 (Web Text))

Max Activating Token Index: 816