Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1245 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.5001. Min Act: -0.0000

Data Index: 1129148 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.8518. Min Act: -0.0000

Data Index: 567140 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.7636. Min Act: -0.0000

Data Index: 1295049 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.0166. Min Act: -0.0000

Data Index: 800909 (The Pile)

Max Activating Token Index: 906

Text #4

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.3532. Min Act: -0.0000

Data Index: 437739 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.2740. Min Act: -0.0000

Data Index: 353579 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.2197. Min Act: -0.0000

Data Index: 1407616 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.2192. Min Act: -0.0000

Data Index: 176592 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.0053. Min Act: -0.0000

Data Index: 1495883 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.3534. Min Act: -0.0000

Data Index: 838218 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 7.8518. Min Range: -7.8518

Max Act: 6.9462. Min Act: -0.0000

Data Index: 1616892 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.3555. Min Act: -0.0000

Data Index: 773404 (The Pile)

Max Activating Token Index: 1018

Text #12

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.1281. Min Act: -0.0000

Data Index: 661230 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.2828. Min Act: -0.0000

Data Index: 1295422 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 7.8518. Min Range: -7.8518

Max Act: 6.6118. Min Act: -0.0000

Data Index: 1985574 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 7.8518. Min Range: -7.8518

Max Act: 6.9878. Min Act: -0.0000

Data Index: 1357378 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 7.8518. Min Range: -7.8518

Max Act: 7.1578. Min Act: -0.0000

Data Index: 1694317 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 7.8518. Min Range: -7.8518

Max Act: 6.6094. Min Act: -0.0000

Data Index: 369698 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 7.8518. Min Range: -7.8518

Max Act: 6.9560. Min Act: -0.0000

Data Index: 166251 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 7.8518. Min Range: -7.8518

Max Act: 6.9403. Min Act: -0.0000

Data Index: 172483 (The Pile)

Max Activating Token Index: 685