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

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

Neuron 2972 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.7205. Min Act: -0.0000

Data Index: 158854 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.4576. Min Act: -0.0000

Data Index: 740734 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.4121. Min Act: -0.0000

Data Index: 1235241 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3006. Min Act: -0.0000

Data Index: 1613646 (Python Code)

Max Activating Token Index: 40

Text #4

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3300. Min Act: -0.0000

Data Index: 1035046 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1607430 (Python Code)

Max Activating Token Index: 242

Text #6

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.1974. Min Act: -0.0000

Data Index: 502736 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1497888 (Python Code)

Max Activating Token Index: 271

Text #8

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.0849. Min Act: -0.0000

Data Index: 829245 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.1873. Min Act: -0.0000

Data Index: 1381326 (Python Code)

Max Activating Token Index: 898

Text #10

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.1723. Min Act: -0.0000

Data Index: 124874 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 1.7205. Min Range: -1.7205

Max Act: 0.9776. Min Act: -0.0000

Data Index: 998598 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1643534 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1413452 (Python Code)

Max Activating Token Index: 540

Text #14

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1041965 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.0731. Min Act: -0.0000

Data Index: 211919 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 1.7205. Min Range: -1.7205

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1431071 (Python Code)

Max Activating Token Index: 721

Text #17

Max Range: 1.7205. Min Range: -1.7205

Max Act: 0.9565. Min Act: -0.0000

Data Index: 753356 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 1.7205. Min Range: -1.7205

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1357003 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 1.7205. Min Range: -1.7205

Max Act: 0.9650. Min Act: 0.0000

Data Index: 1012416 (C4 (Web Text))

Max Activating Token Index: 641