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

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

Neuron 1847 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3523. Min Range: -7.3523

Max Act: 7.2898. Min Act: -0.1700

Data Index: 643835 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 7.3523. Min Range: -7.3523

Max Act: 7.3523. Min Act: -0.1699

Data Index: 872517 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 7.3523. Min Range: -7.3523

Max Act: 7.0710. Min Act: -0.1699

Data Index: 928899 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 7.3523. Min Range: -7.3523

Max Act: 7.0085. Min Act: -0.1700

Data Index: 902597 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.9460. Min Act: -0.1700

Data Index: 662205 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.8835. Min Act: -0.1700

Data Index: 1128895 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.9148. Min Act: -0.1700

Data Index: 144564 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.9460. Min Act: -0.1700

Data Index: 692862 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.8835. Min Act: -0.1700

Data Index: 1293781 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.8523. Min Act: -0.1699

Data Index: 1213514 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.7585. Min Act: -0.1700

Data Index: 771812 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.7585. Min Act: -0.1699

Data Index: 976855 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.7585. Min Act: -0.1700

Data Index: 833999 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.7585. Min Act: -0.1700

Data Index: 1207312 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.6648. Min Act: -0.1700

Data Index: 309372 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.6960. Min Act: -0.1700

Data Index: 402793 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.6960. Min Act: -0.1700

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.4460. Min Act: -0.1700

Data Index: 387268 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.4148. Min Act: -0.1697

Data Index: 517932 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 7.3523. Min Range: -7.3523

Max Act: 6.4148. Min Act: -0.1700

Data Index: 706730 (C4 (Web Text))

Max Activating Token Index: 404