Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 794 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2748. Min Act: -0.0003

Data Index: 480200 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2703. Min Act: -0.0003

Data Index: 1328475 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2601. Min Act: -0.0003

Data Index: 732912 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2673. Min Act: -0.0003

Data Index: 809443 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2550. Min Act: -0.0003

Data Index: 1069677 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2604. Min Act: -0.0003

Data Index: 740119 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2598. Min Act: -0.0003

Data Index: 1129619 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2583. Min Act: -0.0003

Data Index: 602377 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2593. Min Act: -0.0003

Data Index: 71922 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2604. Min Act: -0.0003

Data Index: 486036 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2371. Min Act: -0.0003

Data Index: 418456 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2456. Min Act: -0.0003

Data Index: 448662 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2164. Min Act: -0.0003

Data Index: 844526 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2515. Min Act: -0.0003

Data Index: 1330020 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2602. Min Act: -0.0003

Data Index: 1281026 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2506. Min Act: -0.0003

Data Index: 280798 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2594. Min Act: -0.0003

Data Index: 522303 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2397. Min Act: -0.0003

Data Index: 229399 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2394. Min Act: -0.0003

Data Index: 3621 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2380. Min Act: -0.0003

Data Index: 748672 (C4 (Web Text))

Max Activating Token Index: 689