Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3704 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5556. Min Act: -0.0000

Data Index: 145401 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5400. Min Act: -0.0000

Data Index: 510657 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5496. Min Act: -0.0000

Data Index: 756914 (The Pile)

Max Activating Token Index: 305

Text #3

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5312. Min Act: -0.0000

Data Index: 951560 (The Pile)

Max Activating Token Index: 155

Text #4

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5148. Min Act: -0.0000

Data Index: 1044315 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5343. Min Act: -0.0000

Data Index: 798797 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5128. Min Act: -0.0000

Data Index: 366555 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5270. Min Act: -0.0000

Data Index: 1249868 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.4831. Min Act: -0.0000

Data Index: 1391245 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5316. Min Act: -0.0000

Data Index: 27391 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5217. Min Act: -0.0000

Data Index: 408531 (The Pile)

Max Activating Token Index: 161

Text #11

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.4409. Min Act: -0.0000

Data Index: 1885353 (The Pile)

Max Activating Token Index: 102

Text #12

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.4434. Min Act: -0.0000

Data Index: 533068 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.4520. Min Act: 0.0000

Data Index: 1818919 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5219. Min Act: -0.0000

Data Index: 1229032 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.4033. Min Act: -0.0000

Data Index: 267290 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1702012 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.4222. Min Act: -0.0000

Data Index: 1621748 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.4719. Min Act: 0.0000

Data Index: 808812 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.3456. Min Act: -0.0000

Data Index: 1520302 (The Pile)

Max Activating Token Index: 203