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

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

Neuron 4887 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.5194. Min Act: -0.0000

Data Index: 1275303 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.2908. Min Act: -0.0000

Data Index: 1140618 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.2599. Min Act: -0.0001

Data Index: 1311093 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.2404. Min Act: -0.0000

Data Index: 469677 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.2055. Min Act: -0.0000

Data Index: 1310376 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.1575. Min Act: -0.0000

Data Index: 845796 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.1005. Min Act: -0.0000

Data Index: 517093 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.1169. Min Act: -0.0001

Data Index: 954361 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.1467. Min Act: -0.0000

Data Index: 698100 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.1362. Min Act: -0.0000

Data Index: 1008554 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.0995. Min Act: -0.0000

Data Index: 324366 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.1221. Min Act: -0.0000

Data Index: 469515 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.1567. Min Act: -0.0000

Data Index: 936966 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.0147. Min Act: -0.0000

Data Index: 468386 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.0904. Min Act: -0.0000

Data Index: 650860 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.0823. Min Act: -0.0000

Data Index: 902720 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1207131 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1279157 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.0335. Min Act: -0.0000

Data Index: 917920 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.5194. Min Range: -1.5194

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1252790 (C4 (Web Text))

Max Activating Token Index: 273