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

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

Neuron 3936 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: 0.0373. Min Range: -0.0373

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1345084 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1248795 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0314. Min Act: -0.0003

Data Index: 936298 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0307. Min Act: -0.0003

Data Index: 9906 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1053280 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0292. Min Act: -0.0003

Data Index: 869561 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0311. Min Act: -0.0003

Data Index: 533865 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0300. Min Act: -0.0003

Data Index: 3239 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0301. Min Act: -0.0002

Data Index: 809005 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1253001 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0292. Min Act: -0.0003

Data Index: 105046 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0293. Min Act: -0.0003

Data Index: 140165 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0294. Min Act: -0.0003

Data Index: 398561 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0289. Min Act: -0.0003

Data Index: 347036 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0290. Min Act: -0.0003

Data Index: 913736 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0292. Min Act: -0.0003

Data Index: 769386 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0288. Min Act: -0.0003

Data Index: 706120 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0280. Min Act: -0.0003

Data Index: 806553 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0275. Min Act: -0.0003

Data Index: 900599 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0288. Min Act: -0.0003

Data Index: 872648 (C4 (Web Text))

Max Activating Token Index: 579