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

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

Neuron 3115 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: 0.0288. Min Range: -0.0288

Max Act: 0.0288. Min Act: -0.0003

Data Index: 792853 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1501155 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0225. Min Act: -0.0004

Data Index: 667694 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0262. Min Act: -0.0003

Data Index: 932372 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0268. Min Act: -0.0003

Data Index: 199121 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1031295 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1382597 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0186. Min Act: -0.0003

Data Index: 616282 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1408430 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1457200 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1583160 (Python Code)

Max Activating Token Index: 202

Text #11

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0208. Min Act: -0.0003

Data Index: 633505 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0217. Min Act: -0.0003

Data Index: 611864 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0212. Min Act: -0.0003

Data Index: 903883 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0219. Min Act: -0.0003

Data Index: 29647 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1470104 (Python Code)

Max Activating Token Index: 90

Text #16

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1269239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1484205 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1613395 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0216. Min Act: -0.0003

Data Index: 394791 (C4 (Web Text))

Max Activating Token Index: 1023