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

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

Neuron 3648 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0393. Min Act: -0.0000

Data Index: 373394 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0406. Min Act: -0.0000

Data Index: 616741 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1239334 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0369. Min Act: -0.0000

Data Index: 164105 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1433645 (Python Code)

Max Activating Token Index: 615

Text #5

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0323. Min Act: -0.0000

Data Index: 959878 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0319. Min Act: -0.0000

Data Index: 1574410 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0300. Min Act: -0.0000

Data Index: 549670 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0297. Min Act: -0.0000

Data Index: 323774 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1527499 (Python Code)

Max Activating Token Index: 898

Text #10

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0308. Min Act: -0.0000

Data Index: 225142 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1081935 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0305. Min Act: -0.0000

Data Index: 552402 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0286. Min Act: -0.0000

Data Index: 99173 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0306. Min Act: -0.0000

Data Index: 1033369 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0293. Min Act: -0.0000

Data Index: 1017881 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0280. Min Act: -0.0000

Data Index: 1568084 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0299. Min Act: -0.0000

Data Index: 1417410 (Python Code)

Max Activating Token Index: 248

Text #18

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0285. Min Act: -0.0000

Data Index: 350740 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0293. Min Act: -0.0000

Data Index: 629755 (C4 (Web Text))

Max Activating Token Index: 409