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

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

Neuron 397 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: 0.3875. Min Range: -0.3875

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1092893 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1098051 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3472. Min Act: -0.0000

Data Index: 126356 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1239723 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3158. Min Act: -0.0000

Data Index: 293947 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2994. Min Act: -0.0000

Data Index: 126337 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2403. Min Act: -0.0000

Data Index: 376524 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2794. Min Act: -0.0000

Data Index: 906529 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2432. Min Act: -0.0000

Data Index: 280861 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2625. Min Act: -0.0000

Data Index: 731147 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2435. Min Act: -0.0000

Data Index: 602380 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2312. Min Act: -0.0000

Data Index: 109888 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2443. Min Act: -0.0000

Data Index: 49594 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1026319 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2463. Min Act: -0.0000

Data Index: 680117 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2284. Min Act: -0.0000

Data Index: 845402 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2661. Min Act: -0.0000

Data Index: 621048 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1530449 (Python Code)

Max Activating Token Index: 766

Text #18

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2309. Min Act: -0.0000

Data Index: 919550 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2274. Min Act: -0.0000

Data Index: 700890 (C4 (Web Text))

Max Activating Token Index: 510