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

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

Neuron 2271 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1278792 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.9299. Min Act: -0.0000

Data Index: 863496 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.9331. Min Act: -0.0000

Data Index: 106279 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.9183. Min Act: -0.0000

Data Index: 487860 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.7231. Min Act: -0.0000

Data Index: 395627 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.7612. Min Act: -0.0000

Data Index: 584248 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.7077. Min Act: -0.0000

Data Index: 883872 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6667. Min Act: -0.0000

Data Index: 452738 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1246923 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1186319 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6739. Min Act: -0.0000

Data Index: 553660 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1070383 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6524. Min Act: -0.0000

Data Index: 684206 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1353385 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6232. Min Act: -0.0000

Data Index: 167676 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6170. Min Act: -0.0000

Data Index: 24636 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1085729 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6042. Min Act: -0.0000

Data Index: 478441 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5777. Min Act: -0.0000

Data Index: 222803 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5774. Min Act: -0.0000

Data Index: 158137 (C4 (Web Text))

Max Activating Token Index: 948