Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 655 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0915. Min Act: -0.0006

Data Index: 828846 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0843. Min Act: -0.0006

Data Index: 481990 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0769. Min Act: -0.0006

Data Index: 1210880 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0759. Min Act: -0.0006

Data Index: 194523 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0686. Min Act: -0.0006

Data Index: 553534 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0711. Min Act: -0.0006

Data Index: 891240 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0703. Min Act: -0.0006

Data Index: 177747 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0606. Min Act: -0.0006

Data Index: 476357 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0676. Min Act: -0.0006

Data Index: 420858 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0592. Min Act: -0.0006

Data Index: 1177504 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0632. Min Act: -0.0006

Data Index: 309652 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0597. Min Act: -0.0006

Data Index: 465371 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0573. Min Act: -0.0006

Data Index: 284166 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0561. Min Act: -0.0006

Data Index: 1038575 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0541. Min Act: -0.0006

Data Index: 631017 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0509. Min Act: -0.0006

Data Index: 1019429 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0498. Min Act: -0.0006

Data Index: 453245 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0528. Min Act: -0.0006

Data Index: 620831 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0459. Min Act: -0.0006

Data Index: 1150358 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0508. Min Act: -0.0006

Data Index: 15323 (C4 (Web Text))

Max Activating Token Index: 402