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

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

Neuron 716 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1533229 (Python Code)

Max Activating Token Index: 780

Text #1

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1656753 (Python Code)

Max Activating Token Index: 792

Text #2

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1614872 (Python Code)

Max Activating Token Index: 744

Text #3

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1030234 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1598019 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1640344 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1073943 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0306. Min Act: -0.0003

Data Index: 570843 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1464561 (Python Code)

Max Activating Token Index: 196

Text #9

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1645814 (Python Code)

Max Activating Token Index: 518

Text #10

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0290. Min Act: -0.0003

Data Index: 8357 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0293. Min Act: -0.0002

Data Index: 901707 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1452763 (Python Code)

Max Activating Token Index: 933

Text #13

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0281. Min Act: -0.0004

Data Index: 983028 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0275. Min Act: -0.0003

Data Index: 803742 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1559275 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1332448 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0279. Min Act: -0.0003

Data Index: 231097 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1229330 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1390333 (Python Code)

Max Activating Token Index: 358