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

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

Neuron 4158 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2546. Min Act: -0.0000

Data Index: 175241 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1134139 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2246. Min Act: -0.0000

Data Index: 912706 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2142. Min Act: -0.0000

Data Index: 357632 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2179. Min Act: -0.0000

Data Index: 558145 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2266. Min Act: -0.0000

Data Index: 867891 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1180652 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2249. Min Act: -0.0000

Data Index: 540562 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2142. Min Act: -0.0000

Data Index: 817182 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2125. Min Act: -0.0000

Data Index: 712839 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1084266 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2173. Min Act: -0.0000

Data Index: 37065 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2171. Min Act: -0.0000

Data Index: 721571 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1018236 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2074. Min Act: -0.0000

Data Index: 92316 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2077. Min Act: -0.0000

Data Index: 507261 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2058. Min Act: -0.0000

Data Index: 92104 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1097676 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2115. Min Act: -0.0000

Data Index: 273347 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2099. Min Act: -0.0000

Data Index: 530901 (C4 (Web Text))

Max Activating Token Index: 835