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

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

Neuron 3759 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7585. Min Act: -0.0000

Data Index: 658269 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1013249 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1335092 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1210170 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6340. Min Act: -0.0000

Data Index: 435555 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6718. Min Act: -0.0000

Data Index: 169235 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6565. Min Act: -0.0000

Data Index: 915936 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6780. Min Act: -0.0000

Data Index: 333371 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7120. Min Act: -0.0000

Data Index: 171329 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6586. Min Act: -0.0000

Data Index: 131626 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6251. Min Act: -0.0000

Data Index: 828592 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1340854 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1020841 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6385. Min Act: -0.0000

Data Index: 289801 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6449. Min Act: -0.0000

Data Index: 706683 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6232. Min Act: -0.0000

Data Index: 505113 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6208. Min Act: -0.0000

Data Index: 794816 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6106. Min Act: -0.0000

Data Index: 805423 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6122. Min Act: -0.0000

Data Index: 112097 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1338466 (C4 (Web Text))

Max Activating Token Index: 585