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

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

Neuron 2345 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.6614. Min Act: -0.0001

Data Index: 350494 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.6790. Min Act: -0.0001

Data Index: 1293032 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.6047. Min Act: -0.0001

Data Index: 1152024 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.3462. Min Act: -0.0000

Data Index: 1340966 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.4379. Min Act: -0.0001

Data Index: 697298 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.3170. Min Act: -0.0001

Data Index: 134391 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.4028. Min Act: -0.0001

Data Index: 1326963 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.3878. Min Act: -0.0001

Data Index: 338171 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.2398. Min Act: -0.0000

Data Index: 1166237 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.2938. Min Act: -0.0001

Data Index: 1050886 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.2896. Min Act: -0.0001

Data Index: 738355 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.2435. Min Act: -0.0000

Data Index: 154116 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.3006. Min Act: -0.0001

Data Index: 74525 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.2040. Min Act: -0.0000

Data Index: 372843 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.2771. Min Act: -0.0000

Data Index: 206510 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.3170. Min Act: -0.0001

Data Index: 353642 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.3156. Min Act: -0.0000

Data Index: 138227 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1038311 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.2280. Min Act: -0.0001

Data Index: 421392 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 1.6790. Min Range: -1.6790

Max Act: 1.1671. Min Act: -0.0000

Data Index: 932334 (C4 (Web Text))

Max Activating Token Index: 4