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

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

Neuron 1005 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.3587. Min Act: -0.1700

Data Index: 455205 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.2649. Min Act: -0.1700

Data Index: 387686 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.2962. Min Act: -0.1700

Data Index: 936876 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.2337. Min Act: -0.1700

Data Index: 1083916 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.2024. Min Act: -0.1700

Data Index: 1004477 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.2337. Min Act: -0.1700

Data Index: 736236 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.2337. Min Act: -0.1700

Data Index: 47368 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.1712. Min Act: -0.1700

Data Index: 1163300 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.1712. Min Act: -0.1700

Data Index: 964526 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.1712. Min Act: -0.1700

Data Index: 870247 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.2024. Min Act: -0.1700

Data Index: 388430 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.2024. Min Act: -0.1700

Data Index: 270904 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.2024. Min Act: -0.1700

Data Index: 411048 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.1399. Min Act: -0.1700

Data Index: 191905 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.1712. Min Act: -0.1700

Data Index: 36088 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.1712. Min Act: -0.1700

Data Index: 471066 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.1399. Min Act: -0.1700

Data Index: 173861 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.1399. Min Act: -0.1700

Data Index: 787720 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.1399. Min Act: -0.1700

Data Index: 22153 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 5.3587. Min Range: -5.3587

Max Act: 5.1399. Min Act: -0.1700

Data Index: 563438 (C4 (Web Text))

Max Activating Token Index: 178