Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1633 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0216. Min Act: -0.0003

Data Index: 954643 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1140912 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0208. Min Act: -0.0004

Data Index: 707911 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0199. Min Act: -0.0003

Data Index: 586550 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0204. Min Act: -0.0003

Data Index: 293930 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0195. Min Act: -0.0004

Data Index: 755946 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0195. Min Act: -0.0003

Data Index: 597835 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0195. Min Act: -0.0003

Data Index: 465162 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0197. Min Act: -0.0003

Data Index: 455795 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0191. Min Act: -0.0003

Data Index: 527270 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0191. Min Act: -0.0003

Data Index: 356008 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1069729 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0186. Min Act: -0.0003

Data Index: 845196 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1035170 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0185. Min Act: -0.0003

Data Index: 276196 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0178. Min Act: -0.0004

Data Index: 697684 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0190. Min Act: -0.0003

Data Index: 684521 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0185. Min Act: -0.0003

Data Index: 406932 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0187. Min Act: -0.0003

Data Index: 517098 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0183. Min Act: -0.0003

Data Index: 187591 (C4 (Web Text))

Max Activating Token Index: 264