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

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

Neuron 3072 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8248. Min Range: -5.8248

Max Act: 5.8248. Min Act: -0.0000

Data Index: 1023086 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 5.8248. Min Range: -5.8248

Max Act: 4.5336. Min Act: -0.0000

Data Index: 1342377 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 5.8248. Min Range: -5.8248

Max Act: 4.6203. Min Act: -0.0000

Data Index: 1143078 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.3194. Min Act: -0.0000

Data Index: 803683 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.9302. Min Act: -0.0000

Data Index: 586728 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 5.8248. Min Range: -5.8248

Max Act: 4.1377. Min Act: -0.0000

Data Index: 1088199 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.7723. Min Act: -0.0000

Data Index: 642181 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.5112. Min Act: -0.0000

Data Index: 611487 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.4992. Min Act: -0.0000

Data Index: 173734 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.1219. Min Act: -0.0000

Data Index: 394804 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.2868. Min Act: -0.0000

Data Index: 1319023 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.2518. Min Act: -0.0000

Data Index: 1132675 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.5270. Min Act: -0.0000

Data Index: 1079719 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.3760. Min Act: -0.0000

Data Index: 955716 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.1803. Min Act: -0.0000

Data Index: 129192 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.2083. Min Act: -0.0000

Data Index: 1294629 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.4179. Min Act: -0.0000

Data Index: 394166 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.2055. Min Act: -0.0000

Data Index: 1437710 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.1608. Min Act: -0.0000

Data Index: 830974 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 5.8248. Min Range: -5.8248

Max Act: 3.1419. Min Act: -0.0000

Data Index: 281502 (C4 (Web Text))

Max Activating Token Index: 267