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

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

Neuron 2215 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0510. Min Act: -0.0002

Data Index: 379999 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1077968 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0366. Min Act: -0.0002

Data Index: 82178 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0340. Min Act: -0.0002

Data Index: 29395 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0312. Min Act: -0.0002

Data Index: 142697 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1289703 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1196006 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1211607 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0324. Min Act: -0.0002

Data Index: 258762 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0296. Min Act: -0.0002

Data Index: 997032 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0294. Min Act: -0.0002

Data Index: 265932 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0300. Min Act: -0.0002

Data Index: 393475 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1185724 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0286. Min Act: -0.0002

Data Index: 329764 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0280. Min Act: -0.0002

Data Index: 211840 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0283. Min Act: -0.0002

Data Index: 295132 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1123343 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0266. Min Act: -0.0002

Data Index: 778967 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0275. Min Act: -0.0002

Data Index: 3818 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0259. Min Act: -0.0002

Data Index: 995016 (C4 (Web Text))

Max Activating Token Index: 65