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

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

Neuron 4835 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5870. Min Act: -0.0003

Data Index: 336518 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5699. Min Act: -0.0003

Data Index: 1151998 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5812. Min Act: -0.0003

Data Index: 264757 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5815. Min Act: -0.0003

Data Index: 416499 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5704. Min Act: -0.0002

Data Index: 455599 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5484. Min Act: -0.0003

Data Index: 643020 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5310. Min Act: -0.0002

Data Index: 716153 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5474. Min Act: -0.0002

Data Index: 1077377 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5150. Min Act: -0.0003

Data Index: 249037 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5081. Min Act: -0.0002

Data Index: 220048 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5309. Min Act: -0.0003

Data Index: 682566 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5024. Min Act: -0.0003

Data Index: 755839 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5182. Min Act: -0.0003

Data Index: 982171 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5176. Min Act: -0.0003

Data Index: 807643 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5340. Min Act: -0.0003

Data Index: 12783 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4978. Min Act: -0.0003

Data Index: 8796 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5174. Min Act: -0.0003

Data Index: 1351399 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5134. Min Act: -0.0003

Data Index: 349631 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5273. Min Act: -0.0003

Data Index: 692915 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5087. Min Act: -0.0003

Data Index: 747173 (C4 (Web Text))

Max Activating Token Index: 344