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

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

Neuron 441 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0319. Min Act: -0.0000

Data Index: 652099 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0001

Data Index: 521734 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1397916 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1647937 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0327. Min Act: -0.0000

Data Index: 400857 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0304. Min Act: -0.0000

Data Index: 260424 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1436789 (Python Code)

Max Activating Token Index: 491

Text #7

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0318. Min Act: -0.0001

Data Index: 771101 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0281. Min Act: -0.0000

Data Index: 1443236 (Python Code)

Max Activating Token Index: 288

Text #9

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0293. Min Act: -0.0000

Data Index: 475120 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0266. Min Act: -0.0001

Data Index: 886701 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0285. Min Act: -0.0000

Data Index: 595831 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0275. Min Act: -0.0000

Data Index: 333614 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0270. Min Act: -0.0000

Data Index: 702629 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0268. Min Act: -0.0001

Data Index: 171961 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0294. Min Act: -0.0000

Data Index: 451664 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0277. Min Act: -0.0001

Data Index: 818515 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0284. Min Act: -0.0000

Data Index: 735848 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0277. Min Act: -0.0000

Data Index: 574686 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0280. Min Act: -0.0000

Data Index: 585667 (C4 (Web Text))

Max Activating Token Index: 356