Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4974 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0395. Min Act: -0.0003

Data Index: 64455 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0320. Min Act: -0.0002

Data Index: 190847 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1076627 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1239290 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0289. Min Act: -0.0003

Data Index: 713952 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0287. Min Act: -0.0003

Data Index: 486412 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0280. Min Act: -0.0003

Data Index: 946208 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0273. Min Act: -0.0003

Data Index: 198581 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0276. Min Act: -0.0003

Data Index: 457685 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0275. Min Act: -0.0003

Data Index: 879370 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0269. Min Act: -0.0002

Data Index: 573749 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0254. Min Act: -0.0002

Data Index: 133294 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1117957 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1204810 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1121432 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1008734 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0253. Min Act: -0.0003

Data Index: 780250 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0255. Min Act: -0.0002

Data Index: 587089 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0250. Min Act: -0.0003

Data Index: 978327 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0249. Min Act: -0.0003

Data Index: 277598 (C4 (Web Text))

Max Activating Token Index: 690