Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2594 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.7676. Min Act: -0.0000

Data Index: 241221 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.6411. Min Act: -0.0000

Data Index: 1510761 (Python Code)

Max Activating Token Index: 531

Text #2

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.7188. Min Act: -0.0000

Data Index: 1348011 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.5249. Min Act: -0.0000

Data Index: 791722 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.4911. Min Act: -0.0000

Data Index: 436855 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.4034. Min Act: -0.0000

Data Index: 830750 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.4447. Min Act: -0.0000

Data Index: 1521044 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.5224. Min Act: -0.0000

Data Index: 1228863 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.4037. Min Act: -0.0000

Data Index: 391224 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.3983. Min Act: 0.0000

Data Index: 750740 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.3770. Min Act: -0.0000

Data Index: 203705 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.2956. Min Act: -0.0000

Data Index: 1410427 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.4505. Min Act: -0.0000

Data Index: 1492548 (Python Code)

Max Activating Token Index: 95

Text #13

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.3499. Min Act: -0.0000

Data Index: 1039989 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.3302. Min Act: -0.0000

Data Index: 24376 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.2669. Min Act: -0.0000

Data Index: 186802 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.2604. Min Act: -0.0000

Data Index: 1056507 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.3918. Min Act: -0.0000

Data Index: 837974 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.3051. Min Act: -0.0000

Data Index: 500777 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.4568. Min Act: -0.0000

Data Index: 787504 (C4 (Web Text))

Max Activating Token Index: 302