Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 554 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0420. Min Act: -0.0006

Data Index: 496506 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0445. Min Act: -0.0006

Data Index: 1572634 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0427. Min Act: -0.0006

Data Index: 1463744 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1098887 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0412. Min Act: -0.0006

Data Index: 403974 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0401. Min Act: -0.0006

Data Index: 910861 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0429. Min Act: -0.0006

Data Index: 470806 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1364791 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0379. Min Act: -0.0006

Data Index: 1348382 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0396. Min Act: -0.0006

Data Index: 776918 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0354. Min Act: -0.0006

Data Index: 472440 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0403. Min Act: -0.0006

Data Index: 731061 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0362. Min Act: -0.0006

Data Index: 1532840 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0385. Min Act: -0.0006

Data Index: 1081980 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0386. Min Act: -0.0006

Data Index: 1468950 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0400. Min Act: -0.0006

Data Index: 311705 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0381. Min Act: -0.0006

Data Index: 1151884 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0347. Min Act: -0.0006

Data Index: 869019 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0386. Min Act: -0.0006

Data Index: 511076 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0385. Min Act: -0.0006

Data Index: 85824 (C4 (Web Text))

Max Activating Token Index: 516