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

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

Neuron 3880 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1111591 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0338. Min Act: -0.0001

Data Index: 741972 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0001

Data Index: 584469 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1656867 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0311. Min Act: -0.0001

Data Index: 121429 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1257624 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0292. Min Act: -0.0001

Data Index: 694351 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0296. Min Act: -0.0001

Data Index: 701258 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1229294 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1445420 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0335. Min Act: -0.0001

Data Index: 350491 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1102949 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1203936 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0303. Min Act: -0.0001

Data Index: 373851 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0281. Min Act: -0.0001

Data Index: 742782 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0252. Min Act: -0.0001

Data Index: 1465176 (Python Code)

Max Activating Token Index: 376

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0288. Min Act: -0.0001

Data Index: 564618 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0268. Min Act: -0.0001

Data Index: 987869 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1182091 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0292. Min Act: -0.0001

Data Index: 833392 (C4 (Web Text))

Max Activating Token Index: 36