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

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

Neuron 652 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: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0003

Data Index: 105662 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1200477 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0486. Min Act: -0.0003

Data Index: 820821 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0490. Min Act: -0.0003

Data Index: 742883 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0463. Min Act: -0.0003

Data Index: 711261 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0462. Min Act: -0.0003

Data Index: 982189 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1039654 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0425. Min Act: -0.0003

Data Index: 331271 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0429. Min Act: -0.0003

Data Index: 694787 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1218202 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0427. Min Act: -0.0003

Data Index: 151860 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0403. Min Act: -0.0003

Data Index: 616713 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0420. Min Act: -0.0003

Data Index: 686311 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0407. Min Act: -0.0003

Data Index: 138853 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0401. Min Act: -0.0003

Data Index: 299906 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0393. Min Act: -0.0003

Data Index: 87117 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1224501 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1414686 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0377. Min Act: -0.0003

Data Index: 435009 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0370. Min Act: -0.0003

Data Index: 824987 (C4 (Web Text))

Max Activating Token Index: 729