Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2000 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1078. Min Range: -1.1078

Max Act: 1.0713. Min Act: -0.0000

Data Index: 148678 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 1.1078. Min Range: -1.1078

Max Act: 1.1078. Min Act: -0.0000

Data Index: 1627177 (The Pile)

Max Activating Token Index: 449

Text #2

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1359798 (The Pile)

Max Activating Token Index: 282

Text #3

Max Range: 1.1078. Min Range: -1.1078

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1072213 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 1.1078. Min Range: -1.1078

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1002031 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9589. Min Act: -0.0000

Data Index: 1998117 (The Pile)

Max Activating Token Index: 234

Text #6

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1015023 (The Pile)

Max Activating Token Index: 672

Text #7

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1308988 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9707. Min Act: -0.0000

Data Index: 811587 (The Pile)

Max Activating Token Index: 362

Text #9

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8671. Min Act: -0.0000

Data Index: 327363 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8959. Min Act: -0.0000

Data Index: 926386 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8814. Min Act: -0.0000

Data Index: 885974 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8346. Min Act: -0.0000

Data Index: 94248 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1644265 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9293. Min Act: -0.0000

Data Index: 655549 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 1.1078. Min Range: -1.1078

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1595525 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1502678 (The Pile)

Max Activating Token Index: 802

Text #17

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8077. Min Act: -0.0000

Data Index: 750165 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8947. Min Act: -0.0000

Data Index: 618580 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8278. Min Act: -0.0000

Data Index: 790230 (The Pile)

Max Activating Token Index: 416