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

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

Neuron 449 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: 3.7245. Min Range: -3.7245

Max Act: 3.7245. Min Act: -0.1700

Data Index: 290651 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.7089. Min Act: -0.1700

Data Index: 606159 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.6150. Min Act: -0.1700

Data Index: 364004 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.6150. Min Act: -0.1700

Data Index: 1011498 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5523. Min Act: -0.1700

Data Index: 710837 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5836. Min Act: -0.1700

Data Index: 568300 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5680. Min Act: -0.1700

Data Index: 1170041 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5523. Min Act: -0.1700

Data Index: 763076 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5523. Min Act: -0.1700

Data Index: 1070769 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5836. Min Act: -0.1700

Data Index: 267305 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5053. Min Act: -0.1700

Data Index: 872262 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.4897. Min Act: -0.1700

Data Index: 741676 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5053. Min Act: -0.1700

Data Index: 675316 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5367. Min Act: -0.1700

Data Index: 431675 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5367. Min Act: -0.1700

Data Index: 704638 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5210. Min Act: -0.1700

Data Index: 52577 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.4897. Min Act: -0.1700

Data Index: 165768 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.4583. Min Act: -0.1700

Data Index: 291202 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.5053. Min Act: -0.1700

Data Index: 1266568 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 3.7245. Min Range: -3.7245

Max Act: 3.4897. Min Act: -0.1700

Data Index: 1004694 (C4 (Web Text))

Max Activating Token Index: 463