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

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

Neuron 4335 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1422. Min Range: -2.1422

Max Act: 2.1422. Min Act: -0.0000

Data Index: 198526 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.9813. Min Act: -0.0000

Data Index: 1220671 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.7241. Min Act: -0.0000

Data Index: 1259819 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.5331. Min Act: -0.0000

Data Index: 908632 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.5217. Min Act: -0.0000

Data Index: 79637 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1120609 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.3814. Min Act: -0.0000

Data Index: 1229532 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.4397. Min Act: -0.0000

Data Index: 91238 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.4136. Min Act: -0.0000

Data Index: 1041171 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.3269. Min Act: -0.0000

Data Index: 1196933 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.3898. Min Act: -0.0000

Data Index: 779977 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.3091. Min Act: -0.0000

Data Index: 108593 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.2150. Min Act: -0.0000

Data Index: 131213 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.3545. Min Act: -0.0000

Data Index: 1083364 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.3274. Min Act: -0.0000

Data Index: 571635 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.2318. Min Act: -0.0000

Data Index: 1151715 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.2310. Min Act: -0.0000

Data Index: 1138070 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.2326. Min Act: -0.0000

Data Index: 48009 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.3018. Min Act: -0.0000

Data Index: 251272 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 2.1422. Min Range: -2.1422

Max Act: 1.2090. Min Act: -0.0000

Data Index: 1162752 (C4 (Web Text))

Max Activating Token Index: 436