Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5794 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0000

Data Index: 335704 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0317. Min Act: -0.0000

Data Index: 368020 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0228. Min Act: -0.0000

Data Index: 294448 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0390. Min Act: -0.0000

Data Index: 719461 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0229. Min Act: -0.0000

Data Index: 25090 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0281. Min Act: -0.0000

Data Index: 427835 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0308. Min Act: -0.0000

Data Index: 422510 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0261. Min Act: -0.0000

Data Index: 1283045 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0273. Min Act: -0.0000

Data Index: 253087 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0299. Min Act: -0.0000

Data Index: 733320 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0248. Min Act: -0.0000

Data Index: 324226 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0242. Min Act: -0.0000

Data Index: 1439141 (Python Code)

Max Activating Token Index: 490

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0247. Min Act: -0.0000

Data Index: 1174706 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0194. Min Act: -0.0000

Data Index: 252068 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0214. Min Act: -0.0000

Data Index: 700334 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0203. Min Act: -0.0000

Data Index: 763307 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0174. Min Act: -0.0000

Data Index: 595763 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0201. Min Act: -0.0000

Data Index: 909799 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0226. Min Act: -0.0000

Data Index: 315281 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0223. Min Act: -0.0000

Data Index: 1306540 (C4 (Web Text))

Max Activating Token Index: 325