Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 812 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0002

Data Index: 372285 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1283216 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1073720 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0310. Min Act: -0.0002

Data Index: 531890 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0313. Min Act: -0.0001

Data Index: 655185 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0295. Min Act: -0.0001

Data Index: 548247 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0291. Min Act: -0.0002

Data Index: 80057 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1053846 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0270. Min Act: -0.0002

Data Index: 452842 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0272. Min Act: -0.0001

Data Index: 648348 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1206294 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0256. Min Act: -0.0002

Data Index: 426795 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0262. Min Act: -0.0001

Data Index: 356669 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1605554 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1598234 (Python Code)

Max Activating Token Index: 352

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0270. Min Act: -0.0002

Data Index: 528404 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0265. Min Act: -0.0001

Data Index: 278596 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0265. Min Act: -0.0001

Data Index: 692595 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0259. Min Act: -0.0002

Data Index: 733010 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0267. Min Act: -0.0002

Data Index: 604948 (C4 (Web Text))

Max Activating Token Index: 479