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

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

Neuron 1715 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.3203. Min Act: -0.0000

Data Index: 964692 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.3030. Min Act: -0.0000

Data Index: 282190 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2572. Min Act: 0.0001

Data Index: 27759 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2548. Min Act: -0.0000

Data Index: 588729 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2229. Min Act: -0.0000

Data Index: 567908 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2278. Min Act: -0.0000

Data Index: 51488 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2191. Min Act: -0.0000

Data Index: 522779 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2103. Min Act: 0.0000

Data Index: 359842 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2158. Min Act: -0.0000

Data Index: 36171 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2154. Min Act: -0.0000

Data Index: 449969 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2151. Min Act: 0.0000

Data Index: 533764 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2042. Min Act: -0.0000

Data Index: 274391 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2188. Min Act: 0.0001

Data Index: 174589 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2032. Min Act: -0.0000

Data Index: 717864 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2108. Min Act: 0.0001

Data Index: 190529 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2032. Min Act: 0.0000

Data Index: 968175 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2170. Min Act: -0.0000

Data Index: 742262 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2082. Min Act: 0.0000

Data Index: 238339 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2068. Min Act: 0.0000

Data Index: 492768 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1215833 (C4 (Web Text))

Max Activating Token Index: 864