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

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

Neuron 345 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: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0002

Data Index: 43793 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0503. Min Act: -0.0001

Data Index: 255443 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0483. Min Act: -0.0001

Data Index: 104572 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0484. Min Act: -0.0002

Data Index: 453141 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0456. Min Act: -0.0002

Data Index: 362223 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0464. Min Act: -0.0001

Data Index: 529490 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1355607 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0448. Min Act: -0.0000

Data Index: 700213 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0459. Min Act: -0.0002

Data Index: 302891 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0454. Min Act: -0.0001

Data Index: 354530 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0450. Min Act: -0.0002

Data Index: 337458 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0444. Min Act: -0.0002

Data Index: 566498 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1012763 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0439. Min Act: -0.0002

Data Index: 893029 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0434. Min Act: -0.0002

Data Index: 871783 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1021772 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1087557 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0419. Min Act: -0.0001

Data Index: 635500 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1258699 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0429. Min Act: -0.0002

Data Index: 152990 (C4 (Web Text))

Max Activating Token Index: 120