Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5792 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.8623. Min Act: -0.0000

Data Index: 428974 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7515. Min Act: -0.0000

Data Index: 55369 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1169470 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1407642 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4477. Min Act: -0.0000

Data Index: 495825 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4609. Min Act: -0.0000

Data Index: 343399 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4450. Min Act: -0.0000

Data Index: 104921 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4526. Min Act: -0.0000

Data Index: 492810 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4616. Min Act: -0.0000

Data Index: 888040 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4496. Min Act: -0.0000

Data Index: 528044 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4292. Min Act: -0.0000

Data Index: 36866 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4317. Min Act: -0.0000

Data Index: 848677 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4024. Min Act: -0.0000

Data Index: 995383 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.3890. Min Act: -0.0000

Data Index: 414926 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1032504 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4260. Min Act: -0.0000

Data Index: 515888 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4214. Min Act: -0.0000

Data Index: 991339 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4087. Min Act: -0.0000

Data Index: 337724 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4047. Min Act: -0.0000

Data Index: 758271 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.4022. Min Act: -0.0000

Data Index: 610355 (C4 (Web Text))

Max Activating Token Index: 130