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

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

Neuron 4336 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: 0.0218. Min Range: -0.0218

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1266702 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1062088 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0216. Min Act: -0.0003

Data Index: 98985 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0195. Min Act: -0.0003

Data Index: 629041 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0207. Min Act: -0.0003

Data Index: 257070 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1540600 (Python Code)

Max Activating Token Index: 388

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0195. Min Act: -0.0003

Data Index: 197720 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1337217 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0192. Min Act: -0.0002

Data Index: 609148 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0194. Min Act: -0.0003

Data Index: 397309 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0197. Min Act: -0.0003

Data Index: 83628 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0191. Min Act: -0.0003

Data Index: 68711 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0193. Min Act: -0.0003

Data Index: 28931 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1430444 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0182. Min Act: -0.0003

Data Index: 425893 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0178. Min Act: -0.0002

Data Index: 979749 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1286709 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0178. Min Act: -0.0003

Data Index: 13774 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1581713 (Python Code)

Max Activating Token Index: 558

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0179. Min Act: -0.0003

Data Index: 631034 (C4 (Web Text))

Max Activating Token Index: 34