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

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

Neuron 5247 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: 1.5332. Min Range: -1.5332

Max Act: 1.5332. Min Act: -0.0000

Data Index: 349041 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.4893. Min Act: -0.0000

Data Index: 491031 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1292867 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.4113. Min Act: -0.0000

Data Index: 1300116 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.3771. Min Act: -0.0000

Data Index: 58287 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.3662. Min Act: -0.0000

Data Index: 1258533 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2114. Min Act: 0.0001

Data Index: 1316383 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2702. Min Act: -0.0000

Data Index: 791423 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2765. Min Act: 0.0000

Data Index: 367559 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2321. Min Act: -0.0000

Data Index: 531667 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2001. Min Act: -0.0000

Data Index: 1187771 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2038. Min Act: -0.0000

Data Index: 535235 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2140. Min Act: -0.0000

Data Index: 519507 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.1460. Min Act: -0.0000

Data Index: 247285 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.1675. Min Act: 0.0001

Data Index: 31917 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.1327. Min Act: -0.0000

Data Index: 961493 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.0601. Min Act: -0.0000

Data Index: 96236 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.0461. Min Act: -0.0000

Data Index: 60367 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.0691. Min Act: -0.0000

Data Index: 252990 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.0574. Min Act: 0.0000

Data Index: 1534635 (Python Code)

Max Activating Token Index: 19