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

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

Neuron 4647 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: 0.0453. Min Range: -0.0453

Max Act: 0.0453. Min Act: -0.0002

Data Index: 778846 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1209789 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1228000 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0355. Min Act: -0.0002

Data Index: 194599 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0347. Min Act: -0.0002

Data Index: 129714 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0340. Min Act: -0.0002

Data Index: 973408 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0335. Min Act: -0.0002

Data Index: 9081 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0331. Min Act: -0.0002

Data Index: 429737 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0335. Min Act: -0.0002

Data Index: 481528 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0331. Min Act: -0.0002

Data Index: 790948 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0331. Min Act: -0.0002

Data Index: 204528 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0331. Min Act: -0.0002

Data Index: 498519 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0324. Min Act: -0.0002

Data Index: 358984 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1175250 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1312094 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0311. Min Act: -0.0002

Data Index: 869971 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0327. Min Act: -0.0002

Data Index: 249695 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1338066 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0312. Min Act: -0.0002

Data Index: 383548 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1291266 (C4 (Web Text))

Max Activating Token Index: 587