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

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

Neuron 2805 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: 0.0484. Min Range: -0.0484

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1181767 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0002

Data Index: 697386 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0437. Min Act: -0.0003

Data Index: 590519 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0466. Min Act: -0.0003

Data Index: 950732 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0417. Min Act: -0.0003

Data Index: 894720 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1082471 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0366. Min Act: -0.0002

Data Index: 56474 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1324574 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0411. Min Act: -0.0003

Data Index: 765631 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0425. Min Act: -0.0003

Data Index: 712106 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0412. Min Act: -0.0003

Data Index: 871922 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1063271 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0401. Min Act: -0.0003

Data Index: 580091 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0373. Min Act: -0.0003

Data Index: 548802 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0292. Min Act: -0.0002

Data Index: 202961 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1330245 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0349. Min Act: -0.0002

Data Index: 85243 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0428. Min Act: -0.0003

Data Index: 481510 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0351. Min Act: -0.0003

Data Index: 731512 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1128743 (C4 (Web Text))

Max Activating Token Index: 636