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

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

Neuron 218 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0004

Data Index: 958696 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0253. Min Act: -0.0004

Data Index: 569681 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0244. Min Act: -0.0004

Data Index: 112417 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0229. Min Act: -0.0004

Data Index: 1330838 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0222. Min Act: -0.0004

Data Index: 1080851 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0230. Min Act: -0.0004

Data Index: 1169519 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0233. Min Act: -0.0004

Data Index: 623109 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0223. Min Act: -0.0004

Data Index: 1344749 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0222. Min Act: -0.0004

Data Index: 81076 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0242. Min Act: -0.0004

Data Index: 813971 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0221. Min Act: -0.0004

Data Index: 85295 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0220. Min Act: -0.0004

Data Index: 209587 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0231. Min Act: -0.0004

Data Index: 713845 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0218. Min Act: -0.0004

Data Index: 889131 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0244. Min Act: -0.0004

Data Index: 573971 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0215. Min Act: -0.0004

Data Index: 390470 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0213. Min Act: -0.0004

Data Index: 388518 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0218. Min Act: -0.0004

Data Index: 469036 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0221. Min Act: -0.0004

Data Index: 1230609 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0208. Min Act: -0.0004

Data Index: 427838 (C4 (Web Text))

Max Activating Token Index: 142