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

Dataset: The Pile

Neuron 998 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7310. Min Act: -0.0000

Data Index: 1249653 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.5543. Min Act: -0.0000

Data Index: 1287906 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6021. Min Act: -0.0000

Data Index: 506228 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.5672. Min Act: -0.0000

Data Index: 1939996 (The Pile)

Max Activating Token Index: 171

Text #4

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.4291. Min Act: -0.0000

Data Index: 834818 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.4334. Min Act: -0.0000

Data Index: 1292864 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.5014. Min Act: -0.0000

Data Index: 1896982 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.4095. Min Act: -0.0000

Data Index: 707651 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3271. Min Act: -0.0000

Data Index: 937984 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.4570. Min Act: -0.0000

Data Index: 1411969 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.2955. Min Act: -0.0000

Data Index: 1049319 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.2828. Min Act: -0.0000

Data Index: 473042 (The Pile)

Max Activating Token Index: 815

Text #12

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3669. Min Act: -0.0000

Data Index: 1478070 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.2733. Min Act: -0.0000

Data Index: 921298 (The Pile)

Max Activating Token Index: 94

Text #14

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.2731. Min Act: -0.0000

Data Index: 316058 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1797664 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3720. Min Act: -0.0000

Data Index: 1186841 (The Pile)

Max Activating Token Index: 45

Text #17

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.2999. Min Act: -0.0000

Data Index: 61921 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3558. Min Act: -0.0000

Data Index: 945035 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.2756. Min Act: -0.0000

Data Index: 608513 (The Pile)

Max Activating Token Index: 286