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

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

Neuron 472 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0231. Min Act: -0.0000

Data Index: 668581 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0000

Data Index: 269711 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0221. Min Act: -0.0000

Data Index: 781836 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0204. Min Act: -0.0000

Data Index: 211524 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0201. Min Act: -0.0000

Data Index: 489895 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0199. Min Act: -0.0000

Data Index: 1011270 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0197. Min Act: -0.0000

Data Index: 401273 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0193. Min Act: -0.0000

Data Index: 1226715 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0189. Min Act: -0.0000

Data Index: 281456 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0174. Min Act: -0.0000

Data Index: 70669 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0179. Min Act: -0.0000

Data Index: 850602 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0179. Min Act: -0.0000

Data Index: 1080592 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0184. Min Act: -0.0000

Data Index: 738291 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0169. Min Act: -0.0000

Data Index: 858241 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0189. Min Act: -0.0000

Data Index: 416843 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0180. Min Act: -0.0000

Data Index: 1058827 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0177. Min Act: -0.0000

Data Index: 903170 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0187. Min Act: -0.0000

Data Index: 1040456 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0178. Min Act: -0.0000

Data Index: 321581 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0176. Min Act: -0.0000

Data Index: 700851 (C4 (Web Text))

Max Activating Token Index: 622