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

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

Neuron 678 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0679. Min Act: -0.0001

Data Index: 250222 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0642. Min Act: -0.0001

Data Index: 312681 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0584. Min Act: -0.0001

Data Index: 737643 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0542. Min Act: -0.0000

Data Index: 137822 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0548. Min Act: -0.0000

Data Index: 848923 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0544. Min Act: -0.0000

Data Index: 273520 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1029751 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1188362 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0494. Min Act: -0.0000

Data Index: 659707 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1088156 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0537. Min Act: -0.0000

Data Index: 767385 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1291706 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0482. Min Act: -0.0000

Data Index: 1364026 (Python Code)

Max Activating Token Index: 958

Text #13

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0494. Min Act: -0.0000

Data Index: 1152825 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0483. Min Act: -0.0000

Data Index: 492769 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0451. Min Act: -0.0000

Data Index: 725734 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0432. Min Act: -0.0000

Data Index: 1151081 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1204649 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0439. Min Act: -0.0000

Data Index: 939813 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0430. Min Act: -0.0000

Data Index: 919768 (C4 (Web Text))

Max Activating Token Index: 493