Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 828 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2941. Min Range: -5.2941

Max Act: 5.2941. Min Act: -0.1700

Data Index: 1244445 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 5.2941. Min Range: -5.2941

Max Act: 5.2316. Min Act: -0.1700

Data Index: 145792 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 5.2941. Min Range: -5.2941

Max Act: 5.2004. Min Act: -0.1700

Data Index: 190574 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 5.2941. Min Range: -5.2941

Max Act: 5.0754. Min Act: -0.1700

Data Index: 806586 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 5.2941. Min Range: -5.2941

Max Act: 5.0441. Min Act: -0.1700

Data Index: 320410 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 5.2941. Min Range: -5.2941

Max Act: 5.0754. Min Act: -0.1700

Data Index: 952239 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 5.2941. Min Range: -5.2941

Max Act: 5.0441. Min Act: -0.1700

Data Index: 653020 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 5.2941. Min Range: -5.2941

Max Act: 5.0754. Min Act: -0.1700

Data Index: 1141914 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 5.2941. Min Range: -5.2941

Max Act: 5.0129. Min Act: -0.1700

Data Index: 1239580 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 5.2941. Min Range: -5.2941

Max Act: 4.9816. Min Act: -0.1700

Data Index: 1141335 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 5.2941. Min Range: -5.2941

Max Act: 4.9816. Min Act: -0.1700

Data Index: 1123450 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 5.2941. Min Range: -5.2941

Max Act: 4.9816. Min Act: -0.1700

Data Index: 621656 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 5.2941. Min Range: -5.2941

Max Act: 4.9816. Min Act: -0.1700

Data Index: 1016786 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 5.2941. Min Range: -5.2941

Max Act: 4.9504. Min Act: -0.1700

Data Index: 349296 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 5.2941. Min Range: -5.2941

Max Act: 5.0441. Min Act: -0.1700

Data Index: 1342697 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 5.2941. Min Range: -5.2941

Max Act: 4.9816. Min Act: -0.1700

Data Index: 1235730 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 5.2941. Min Range: -5.2941

Max Act: 4.9191. Min Act: -0.1700

Data Index: 596184 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 5.2941. Min Range: -5.2941

Max Act: 4.9504. Min Act: -0.1700

Data Index: 1360143 (Python Code)

Max Activating Token Index: 748

Text #18

Max Range: 5.2941. Min Range: -5.2941

Max Act: 4.9191. Min Act: -0.1700

Data Index: 790687 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 5.2941. Min Range: -5.2941

Max Act: 4.8566. Min Act: -0.1700

Data Index: 557347 (C4 (Web Text))

Max Activating Token Index: 313