Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 745 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.4315. Min Act: -0.1700

Data Index: 728458 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3844. Min Act: -0.1700

Data Index: 500809 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3688. Min Act: -0.1700

Data Index: 886159 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.4158. Min Act: -0.1700

Data Index: 775086 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3374. Min Act: -0.1700

Data Index: 1350127 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3531. Min Act: -0.1700

Data Index: 75284 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3531. Min Act: -0.1700

Data Index: 1222409 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3688. Min Act: -0.1700

Data Index: 947903 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3374. Min Act: -0.1700

Data Index: 462587 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3217. Min Act: -0.1700

Data Index: 1030714 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3217. Min Act: -0.1700

Data Index: 737705 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3060. Min Act: -0.1700

Data Index: 408684 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3217. Min Act: -0.1700

Data Index: 634204 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3217. Min Act: -0.1700

Data Index: 683983 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3060. Min Act: -0.1700

Data Index: 1043060 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3060. Min Act: -0.1700

Data Index: 1055755 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3060. Min Act: -0.1700

Data Index: 809044 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2903. Min Act: -0.1700

Data Index: 1355766 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3060. Min Act: -0.1700

Data Index: 1143110 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2745. Min Act: -0.1700

Data Index: 1063719 (C4 (Web Text))

Max Activating Token Index: 551