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

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

Neuron 4758 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: 0.2509. Min Range: -0.2509

Max Act: 0.2509. Min Act: -0.0002

Data Index: 705233 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2386. Min Act: -0.0002

Data Index: 304357 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2371. Min Act: -0.0002

Data Index: 684287 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2433. Min Act: -0.0002

Data Index: 460187 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2323. Min Act: -0.0002

Data Index: 401468 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2306. Min Act: -0.0002

Data Index: 670935 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2311. Min Act: -0.0002

Data Index: 814131 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2296. Min Act: -0.0002

Data Index: 66300 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2141. Min Act: -0.0002

Data Index: 1298595 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2112. Min Act: -0.0002

Data Index: 340494 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2247. Min Act: -0.0002

Data Index: 1198858 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2131. Min Act: -0.0002

Data Index: 526602 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2145. Min Act: -0.0002

Data Index: 658663 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2112. Min Act: -0.0002

Data Index: 1022462 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2105. Min Act: -0.0002

Data Index: 1070395 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2093. Min Act: -0.0002

Data Index: 980270 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2141. Min Act: -0.0002

Data Index: 771171 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1995. Min Act: -0.0002

Data Index: 437368 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2131. Min Act: -0.0002

Data Index: 678001 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2011. Min Act: -0.0002

Data Index: 1289048 (C4 (Web Text))

Max Activating Token Index: 789