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

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

Neuron 1981 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: 3.3805. Min Range: -3.3805

Max Act: 3.3805. Min Act: -0.1700

Data Index: 1159086 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.3491. Min Act: -0.1700

Data Index: 1189871 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.3648. Min Act: -0.1700

Data Index: 1229401 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.3491. Min Act: -0.1700

Data Index: 415717 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.3334. Min Act: -0.1700

Data Index: 161936 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.3491. Min Act: -0.1700

Data Index: 1271326 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.3020. Min Act: -0.1700

Data Index: 915862 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.3020. Min Act: -0.1700

Data Index: 766937 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2863. Min Act: -0.1700

Data Index: 928919 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2863. Min Act: -0.1700

Data Index: 1050238 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2549. Min Act: -0.1700

Data Index: 975250 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1197099 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2706. Min Act: -0.1700

Data Index: 66418 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2863. Min Act: -0.1700

Data Index: 177521 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2863. Min Act: -0.1700

Data Index: 336719 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2863. Min Act: -0.1700

Data Index: 962667 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2706. Min Act: -0.1700

Data Index: 455141 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2549. Min Act: -0.1700

Data Index: 893174 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2549. Min Act: -0.1700

Data Index: 839794 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.3805. Min Range: -3.3805

Max Act: 3.2549. Min Act: -0.1700

Data Index: 988962 (C4 (Web Text))

Max Activating Token Index: 303