Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3066 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1327700 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0732. Min Act: -0.0001

Data Index: 976032 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0613. Min Act: -0.0000

Data Index: 861595 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0657. Min Act: -0.0001

Data Index: 248008 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0600. Min Act: -0.0001

Data Index: 150650 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0612. Min Act: -0.0001

Data Index: 127060 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1474381 (Python Code)

Max Activating Token Index: 994

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1053052 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0631. Min Act: -0.0001

Data Index: 464438 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1078485 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1158203 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1259648 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0611. Min Act: -0.0001

Data Index: 337113 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0573. Min Act: -0.0001

Data Index: 576768 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0596. Min Act: -0.0000

Data Index: 376441 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1153284 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0575. Min Act: -0.0001

Data Index: 713697 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1228045 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0636. Min Act: -0.0001

Data Index: 254338 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0553. Min Act: -0.0001

Data Index: 232491 (C4 (Web Text))

Max Activating Token Index: 655