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

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

Neuron 5688 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.4306. Min Act: -0.0000

Data Index: 54835 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3176. Min Act: -0.0000

Data Index: 790503 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2803. Min Act: 0.0000

Data Index: 277213 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2898. Min Act: 0.0000

Data Index: 360866 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1277307 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2316. Min Act: -0.0000

Data Index: 636443 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1113042 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1178073 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2216. Min Act: -0.0000

Data Index: 261271 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2158. Min Act: -0.0000

Data Index: 816285 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2053. Min Act: -0.0000

Data Index: 921489 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1131491 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1304181 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2178. Min Act: -0.0000

Data Index: 516096 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.1972. Min Act: -0.0000

Data Index: 413759 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.1964. Min Act: -0.0000

Data Index: 307881 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1084853 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.1931. Min Act: -0.0000

Data Index: 89366 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2063. Min Act: -0.0000

Data Index: 463617 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1181577 (C4 (Web Text))

Max Activating Token Index: 831