Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1996 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.9211. Min Act: -0.0001

Data Index: 379763 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8208. Min Act: -0.0001

Data Index: 1145572 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6800. Min Act: -0.0000

Data Index: 832759 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6889. Min Act: -0.0000

Data Index: 825154 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5747. Min Act: -0.0001

Data Index: 331542 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5804. Min Act: -0.0001

Data Index: 112301 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1062027 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5840. Min Act: -0.0000

Data Index: 664942 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7035. Min Act: -0.0000

Data Index: 106347 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5177. Min Act: -0.0001

Data Index: 865240 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6931. Min Act: -0.0000

Data Index: 853469 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5965. Min Act: -0.0000

Data Index: 16413 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6259. Min Act: -0.0000

Data Index: 955602 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5865. Min Act: -0.0001

Data Index: 964812 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6345. Min Act: -0.0000

Data Index: 235367 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7193. Min Act: -0.0001

Data Index: 1068594 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6185. Min Act: -0.0001

Data Index: 596905 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5655. Min Act: -0.0001

Data Index: 933496 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.4635. Min Act: -0.0001

Data Index: 1092012 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5514. Min Act: -0.0001

Data Index: 422466 (C4 (Web Text))

Max Activating Token Index: 237