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

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

Neuron 4609 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: 6.2730. Min Range: -6.2730

Max Act: 6.1065. Min Act: -0.0000

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 6.2730. Min Range: -6.2730

Max Act: 6.2730. Min Act: -0.0000

Data Index: 1199958 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 6.2730. Min Range: -6.2730

Max Act: 6.1080. Min Act: -0.0000

Data Index: 648960 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 6.2730. Min Range: -6.2730

Max Act: 6.1611. Min Act: -0.0000

Data Index: 941839 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 6.2730. Min Range: -6.2730

Max Act: 5.6950. Min Act: -0.0000

Data Index: 711790 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 6.2730. Min Range: -6.2730

Max Act: 5.6654. Min Act: -0.0000

Data Index: 743100 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 6.2730. Min Range: -6.2730

Max Act: 5.6224. Min Act: -0.0000

Data Index: 820645 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 6.2730. Min Range: -6.2730

Max Act: 5.4884. Min Act: -0.0000

Data Index: 1269190 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 6.2730. Min Range: -6.2730

Max Act: 5.5207. Min Act: -0.0000

Data Index: 961125 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 6.2730. Min Range: -6.2730

Max Act: 4.6528. Min Act: -0.0000

Data Index: 548999 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 6.2730. Min Range: -6.2730

Max Act: 4.4113. Min Act: -0.0000

Data Index: 229659 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 6.2730. Min Range: -6.2730

Max Act: 4.2890. Min Act: -0.0000

Data Index: 400218 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 6.2730. Min Range: -6.2730

Max Act: 4.2434. Min Act: -0.0000

Data Index: 396376 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 6.2730. Min Range: -6.2730

Max Act: 4.1474. Min Act: -0.0000

Data Index: 675069 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 6.2730. Min Range: -6.2730

Max Act: 4.1267. Min Act: -0.0000

Data Index: 891096 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 6.2730. Min Range: -6.2730

Max Act: 3.8310. Min Act: -0.0000

Data Index: 1197294 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 6.2730. Min Range: -6.2730

Max Act: 3.6955. Min Act: 0.0000

Data Index: 134750 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 6.2730. Min Range: -6.2730

Max Act: 3.6615. Min Act: -0.0000

Data Index: 273353 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 6.2730. Min Range: -6.2730

Max Act: 3.8027. Min Act: -0.0000

Data Index: 998556 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 6.2730. Min Range: -6.2730

Max Act: 3.6310. Min Act: -0.0000

Data Index: 864199 (C4 (Web Text))

Max Activating Token Index: 629