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

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

Neuron 1714 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.2294. Min Act: -0.1700

Data Index: 83420 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.1982. Min Act: -0.1700

Data Index: 467698 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.1982. Min Act: -0.1700

Data Index: 20935 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.1357. Min Act: -0.1700

Data Index: 658190 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.0732. Min Act: -0.1700

Data Index: 600573 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.1044. Min Act: -0.1700

Data Index: 52193 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.0732. Min Act: -0.1700

Data Index: 912324 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.1044. Min Act: -0.1700

Data Index: 1322994 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.0107. Min Act: -0.1700

Data Index: 316036 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.0107. Min Act: -0.1700

Data Index: 200818 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 8.2294. Min Range: -8.2294

Max Act: 7.9482. Min Act: -0.1699

Data Index: 340781 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 8.2294. Min Range: -8.2294

Max Act: 8.0107. Min Act: -0.1700

Data Index: 457831 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 8.2294. Min Range: -8.2294

Max Act: 7.9482. Min Act: -0.1700

Data Index: 779858 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 8.2294. Min Range: -8.2294

Max Act: 7.9794. Min Act: -0.1700

Data Index: 639582 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 8.2294. Min Range: -8.2294

Max Act: 7.7607. Min Act: -0.1700

Data Index: 880979 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 8.2294. Min Range: -8.2294

Max Act: 7.8544. Min Act: -0.1700

Data Index: 457041 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 8.2294. Min Range: -8.2294

Max Act: 7.8857. Min Act: -0.1700

Data Index: 762703 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 8.2294. Min Range: -8.2294

Max Act: 7.8544. Min Act: -0.1700

Data Index: 1140662 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 8.2294. Min Range: -8.2294

Max Act: 7.8232. Min Act: -0.1700

Data Index: 778087 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 8.2294. Min Range: -8.2294

Max Act: 7.8232. Min Act: -0.1700

Data Index: 308935 (C4 (Web Text))

Max Activating Token Index: 341