Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1762 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.6371. Min Act: -0.1700

Data Index: 581655 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.6214. Min Act: -0.1700

Data Index: 600967 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.6058. Min Act: -0.1700

Data Index: 908592 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5745. Min Act: -0.1700

Data Index: 578189 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5901. Min Act: -0.1700

Data Index: 767555 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.6058. Min Act: -0.1700

Data Index: 240600 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5745. Min Act: -0.1700

Data Index: 12660 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5745. Min Act: -0.1700

Data Index: 124193 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5745. Min Act: -0.1700

Data Index: 277841 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5745. Min Act: -0.1700

Data Index: 731984 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5588. Min Act: -0.1700

Data Index: 527447 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5431. Min Act: -0.1700

Data Index: 160190 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5588. Min Act: -0.1700

Data Index: 734766 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5588. Min Act: -0.1700

Data Index: 461486 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5588. Min Act: -0.1700

Data Index: 1359786 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5431. Min Act: -0.1700

Data Index: 424781 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5275. Min Act: -0.1700

Data Index: 579014 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5431. Min Act: -0.1700

Data Index: 328246 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5275. Min Act: -0.1700

Data Index: 696075 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 3.6371. Min Range: -3.6371

Max Act: 3.5431. Min Act: -0.1700

Data Index: 827910 (C4 (Web Text))

Max Activating Token Index: 304