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

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

Neuron 3227 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: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1500101 (Python Code)

Max Activating Token Index: 709

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1165610 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1383730 (Python Code)

Max Activating Token Index: 282

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1558805 (Python Code)

Max Activating Token Index: 649

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1545642 (Python Code)

Max Activating Token Index: 425

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1413710 (Python Code)

Max Activating Token Index: 377

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1607526 (Python Code)

Max Activating Token Index: 808

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1388077 (Python Code)

Max Activating Token Index: 252

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0311. Min Act: -0.0003

Data Index: 974668 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1532245 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1612089 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1459036 (Python Code)

Max Activating Token Index: 808

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1500141 (Python Code)

Max Activating Token Index: 629

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0287. Min Act: -0.0003

Data Index: 31944 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1366621 (Python Code)

Max Activating Token Index: 427

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1416306 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1401556 (Python Code)

Max Activating Token Index: 849

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1178662 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1418957 (Python Code)

Max Activating Token Index: 968

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1589518 (Python Code)

Max Activating Token Index: 314