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

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

Neuron 696 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.7780. Min Act: -0.1700

Data Index: 861582 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6685. Min Act: -0.1700

Data Index: 1058455 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6372. Min Act: -0.1700

Data Index: 1012324 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6059. Min Act: -0.1700

Data Index: 710653 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6372. Min Act: -0.1700

Data Index: 1203495 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6215. Min Act: -0.1700

Data Index: 1640457 (Python Code)

Max Activating Token Index: 426

Text #6

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.5902. Min Act: -0.1700

Data Index: 112586 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6372. Min Act: -0.1700

Data Index: 126278 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6372. Min Act: -0.1700

Data Index: 1617830 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6059. Min Act: -0.1700

Data Index: 808018 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6372. Min Act: -0.1700

Data Index: 848803 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.5902. Min Act: -0.1700

Data Index: 742622 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.5746. Min Act: -0.1700

Data Index: 234812 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.5589. Min Act: -0.1700

Data Index: 261459 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.5746. Min Act: -0.1700

Data Index: 788390 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.5746. Min Act: -0.1700

Data Index: 672596 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.5902. Min Act: -0.1700

Data Index: 137165 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6059. Min Act: -0.1700

Data Index: 1247526 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.6215. Min Act: -0.1700

Data Index: 1395232 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.7780. Min Range: -3.7780

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1079247 (C4 (Web Text))

Max Activating Token Index: 550