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

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

Neuron 5883 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3568. Min Range: -2.3568

Max Act: 2.3568. Min Act: -0.0000

Data Index: 1611420 (Python Code)

Max Activating Token Index: 728

Text #1

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.8697. Min Act: -0.0000

Data Index: 1151360 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.7216. Min Act: -0.0000

Data Index: 312509 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.5436. Min Act: -0.0000

Data Index: 604762 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.6238. Min Act: -0.0000

Data Index: 89267 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.4887. Min Act: -0.0000

Data Index: 100256 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.4770. Min Act: -0.0000

Data Index: 800567 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.5297. Min Act: -0.0000

Data Index: 156391 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.4559. Min Act: -0.0000

Data Index: 105489 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.4402. Min Act: -0.0000

Data Index: 909578 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.5414. Min Act: -0.0000

Data Index: 1005536 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.4079. Min Act: -0.0000

Data Index: 1595950 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.3303. Min Act: -0.0000

Data Index: 823855 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.4841. Min Act: -0.0000

Data Index: 293869 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.2883. Min Act: -0.0000

Data Index: 247468 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.3735. Min Act: -0.0000

Data Index: 541245 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.4459. Min Act: -0.0000

Data Index: 33217 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.1639. Min Act: -0.0000

Data Index: 752248 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.2292. Min Act: -0.0000

Data Index: 609541 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 2.3568. Min Range: -2.3568

Max Act: 1.3009. Min Act: -0.0000

Data Index: 515438 (C4 (Web Text))

Max Activating Token Index: 990