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

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

Neuron 2502 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2204. Min Range: -5.2204

Max Act: 5.2204. Min Act: -0.0000

Data Index: 83518 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.5693. Min Act: -0.0000

Data Index: 164929 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.4384. Min Act: -0.0000

Data Index: 488820 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.3128. Min Act: -0.0000

Data Index: 503441 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.0338. Min Act: -0.0000

Data Index: 1099040 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.1290. Min Act: -0.0000

Data Index: 199946 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 5.2204. Min Range: -5.2204

Max Act: 3.9409. Min Act: -0.0000

Data Index: 671854 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.0908. Min Act: -0.0000

Data Index: 695071 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.0838. Min Act: -0.0000

Data Index: 813402 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.2428. Min Act: -0.0000

Data Index: 1323596 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.2462. Min Act: -0.0000

Data Index: 1020502 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.0638. Min Act: -0.0000

Data Index: 1211826 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.0400. Min Act: -0.0000

Data Index: 535329 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.0408. Min Act: -0.0000

Data Index: 1104253 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.0397. Min Act: -0.0000

Data Index: 278368 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.1848. Min Act: -0.0000

Data Index: 1177273 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 5.2204. Min Range: -5.2204

Max Act: 4.1113. Min Act: -0.0000

Data Index: 938966 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 5.2204. Min Range: -5.2204

Max Act: 3.9732. Min Act: -0.0000

Data Index: 643404 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 5.2204. Min Range: -5.2204

Max Act: 3.9614. Min Act: -0.0000

Data Index: 1221580 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 5.2204. Min Range: -5.2204

Max Act: 3.6121. Min Act: -0.0000

Data Index: 1081963 (C4 (Web Text))

Max Activating Token Index: 933