Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 420 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0006

Data Index: 201228 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0434. Min Act: -0.0006

Data Index: 128316 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0404. Min Act: -0.0006

Data Index: 991612 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0388. Min Act: -0.0006

Data Index: 1240497 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0386. Min Act: -0.0006

Data Index: 606577 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0328. Min Act: -0.0006

Data Index: 1047324 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0311. Min Act: -0.0006

Data Index: 621039 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0311. Min Act: -0.0006

Data Index: 411616 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0291. Min Act: -0.0006

Data Index: 994434 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0286. Min Act: -0.0006

Data Index: 530871 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0281. Min Act: -0.0006

Data Index: 879437 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0292. Min Act: -0.0006

Data Index: 592907 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0306. Min Act: -0.0006

Data Index: 389185 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0271. Min Act: -0.0006

Data Index: 653403 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0313. Min Act: -0.0006

Data Index: 656833 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0291. Min Act: -0.0006

Data Index: 458977 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1355246 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0290. Min Act: -0.0006

Data Index: 19408 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0295. Min Act: -0.0006

Data Index: 735984 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0276. Min Act: -0.0006

Data Index: 932824 (C4 (Web Text))

Max Activating Token Index: 773