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

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

Neuron 1518 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1467214 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0254. Min Act: -0.0001

Data Index: 351709 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0212. Min Act: -0.0000

Data Index: 916031 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0208. Min Act: -0.0000

Data Index: 717849 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0000

Data Index: 146864 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1077791 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1499199 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1003089 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1316057 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0164. Min Act: -0.0001

Data Index: 195206 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0192. Min Act: -0.0000

Data Index: 103994 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1415807 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0180. Min Act: -0.0001

Data Index: 304454 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1615689 (Python Code)

Max Activating Token Index: 428

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1363057 (Python Code)

Max Activating Token Index: 844

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1439498 (Python Code)

Max Activating Token Index: 510

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0178. Min Act: -0.0000

Data Index: 702498 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0180. Min Act: -0.0001

Data Index: 1436667 (Python Code)

Max Activating Token Index: 845

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0181. Min Act: -0.0001

Data Index: 1547775 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1646523 (Python Code)

Max Activating Token Index: 669