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

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

Neuron 105 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: 3.9792. Min Range: -3.9792

Max Act: 3.9792. Min Act: -0.1700

Data Index: 869817 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.5098. Min Act: -0.1700

Data Index: 82980 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.4315. Min Act: -0.1700

Data Index: 1334833 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.4628. Min Act: -0.1700

Data Index: 875103 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.4315. Min Act: -0.1700

Data Index: 131682 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.4158. Min Act: -0.1700

Data Index: 382646 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3844. Min Act: -0.1700

Data Index: 10011 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3844. Min Act: -0.1700

Data Index: 1052958 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3373. Min Act: -0.1700

Data Index: 59169 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3373. Min Act: -0.1700

Data Index: 976507 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3373. Min Act: -0.1700

Data Index: 111044 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.2902. Min Act: -0.1700

Data Index: 1230010 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3373. Min Act: -0.1700

Data Index: 205337 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3216. Min Act: -0.1700

Data Index: 1094679 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3059. Min Act: -0.1700

Data Index: 429693 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3216. Min Act: -0.1700

Data Index: 247731 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3059. Min Act: -0.1700

Data Index: 173903 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.3059. Min Act: -0.1700

Data Index: 1239546 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.2902. Min Act: -0.1700

Data Index: 512209 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.2745. Min Act: -0.1700

Data Index: 541222 (C4 (Web Text))

Max Activating Token Index: 865