Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4628 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1196885 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0361. Min Act: -0.0002

Data Index: 878056 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0348. Min Act: -0.0002

Data Index: 494952 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0348. Min Act: -0.0002

Data Index: 588466 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1086463 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0332. Min Act: -0.0002

Data Index: 834020 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0326. Min Act: -0.0002

Data Index: 749199 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0323. Min Act: -0.0002

Data Index: 758234 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1250989 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0318. Min Act: -0.0002

Data Index: 662782 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1014016 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0316. Min Act: -0.0002

Data Index: 630760 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0320. Min Act: -0.0002

Data Index: 825428 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0312. Min Act: -0.0002

Data Index: 415045 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0312. Min Act: -0.0002

Data Index: 821179 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0307. Min Act: -0.0002

Data Index: 198897 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0304. Min Act: -0.0002

Data Index: 905764 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0310. Min Act: -0.0002

Data Index: 565504 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0303. Min Act: -0.0002

Data Index: 43955 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0302. Min Act: -0.0002

Data Index: 50347 (C4 (Web Text))

Max Activating Token Index: 409