Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 341 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0225. Min Act: -0.0003

Data Index: 94966 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1400103 (Python Code)

Max Activating Token Index: 477

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1276609 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1056003 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1408745 (Python Code)

Max Activating Token Index: 953

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0200. Min Act: -0.0003

Data Index: 254319 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0209. Min Act: -0.0003

Data Index: 671917 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1174708 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1588979 (Python Code)

Max Activating Token Index: 626

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0196. Min Act: -0.0003

Data Index: 264372 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1413011 (Python Code)

Max Activating Token Index: 997

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0193. Min Act: -0.0003

Data Index: 855268 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1452375 (Python Code)

Max Activating Token Index: 186

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1557816 (Python Code)

Max Activating Token Index: 462

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1393038 (Python Code)

Max Activating Token Index: 853

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0196. Min Act: -0.0003

Data Index: 535547 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0186. Min Act: -0.0003

Data Index: 420236 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1571085 (Python Code)

Max Activating Token Index: 646

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1418791 (Python Code)

Max Activating Token Index: 752

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0176. Min Act: -0.0003

Data Index: 953929 (C4 (Web Text))

Max Activating Token Index: 825