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

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

Neuron 2054 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1506522 (Python Code)

Max Activating Token Index: 279

Text #1

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1561046 (Python Code)

Max Activating Token Index: 164

Text #2

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0324. Min Act: -0.0002

Data Index: 546251 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1636266 (Python Code)

Max Activating Token Index: 81

Text #4

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0314. Min Act: -0.0002

Data Index: 796626 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0327. Min Act: -0.0002

Data Index: 825919 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0286. Min Act: -0.0002

Data Index: 856261 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0292. Min Act: -0.0002

Data Index: 773341 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1266958 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1427245 (Python Code)

Max Activating Token Index: 229

Text #10

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1190693 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1372945 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0292. Min Act: -0.0002

Data Index: 167455 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0290. Min Act: -0.0002

Data Index: 677514 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0286. Min Act: -0.0002

Data Index: 519218 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0284. Min Act: -0.0002

Data Index: 557515 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0282. Min Act: -0.0002

Data Index: 301255 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1448463 (Python Code)

Max Activating Token Index: 511

Text #18

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0304. Min Act: -0.0002

Data Index: 619671 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0302. Min Act: -0.0002

Data Index: 305270 (C4 (Web Text))

Max Activating Token Index: 753