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

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

Neuron 1615 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0524. Min Range: -3.0524

Max Act: 3.0524. Min Act: -0.1700

Data Index: 1221826 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9259. Min Act: -0.1700

Data Index: 876034 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.8624. Min Act: -0.1700

Data Index: 749833 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.8306. Min Act: -0.1700

Data Index: 107185 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.8465. Min Act: -0.1700

Data Index: 274705 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.8147. Min Act: -0.1700

Data Index: 710252 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7988. Min Act: -0.1700

Data Index: 735637 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.8147. Min Act: -0.1700

Data Index: 1074668 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7669. Min Act: -0.1700

Data Index: 858025 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7828. Min Act: -0.1700

Data Index: 4966 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7669. Min Act: -0.1700

Data Index: 1059189 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7669. Min Act: -0.1700

Data Index: 279752 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7669. Min Act: -0.1700

Data Index: 329887 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7509. Min Act: -0.1700

Data Index: 1129808 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7509. Min Act: -0.1700

Data Index: 797466 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7350. Min Act: -0.1700

Data Index: 600208 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7350. Min Act: -0.1700

Data Index: 701154 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7350. Min Act: -0.1700

Data Index: 759755 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7030. Min Act: -0.1700

Data Index: 1089792 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.7350. Min Act: -0.1700

Data Index: 1064190 (C4 (Web Text))

Max Activating Token Index: 582