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

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

Neuron 850 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0003

Data Index: 288854 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0223. Min Act: -0.0003

Data Index: 83353 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0221. Min Act: -0.0003

Data Index: 769236 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0003

Data Index: 58296 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0224. Min Act: -0.0003

Data Index: 489288 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0003

Data Index: 455954 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0216. Min Act: -0.0003

Data Index: 454697 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0207. Min Act: -0.0003

Data Index: 749611 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0206. Min Act: -0.0004

Data Index: 516985 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0201. Min Act: -0.0003

Data Index: 270636 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0199. Min Act: -0.0003

Data Index: 176298 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0200. Min Act: -0.0003

Data Index: 540294 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1069930 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0195. Min Act: -0.0004

Data Index: 758701 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0199. Min Act: -0.0003

Data Index: 589899 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0198. Min Act: -0.0004

Data Index: 265330 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0198. Min Act: -0.0003

Data Index: 266339 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0197. Min Act: -0.0004

Data Index: 1025639 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0197. Min Act: -0.0003

Data Index: 888820 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0191. Min Act: -0.0003

Data Index: 456600 (C4 (Web Text))

Max Activating Token Index: 909