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

Dataset: The Pile

Neuron 2327 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.5852. Min Act: -0.0000

Data Index: 953613 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.5071. Min Act: -0.0000

Data Index: 815949 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.3459. Min Act: -0.0000

Data Index: 697879 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.4194. Min Act: -0.0000

Data Index: 1617140 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1530274 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.1051. Min Act: -0.0000

Data Index: 151224 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.1163. Min Act: 0.0000

Data Index: 1229790 (The Pile)

Max Activating Token Index: 891

Text #7

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.1845. Min Act: -0.0000

Data Index: 1404411 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.2516. Min Act: -0.0000

Data Index: 147470 (The Pile)

Max Activating Token Index: 986

Text #9

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.1123. Min Act: -0.0000

Data Index: 248406 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.1381. Min Act: -0.0000

Data Index: 1974773 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1170441 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.1170. Min Act: -0.0000

Data Index: 719517 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.0931. Min Act: -0.0000

Data Index: 891 (The Pile)

Max Activating Token Index: 653

Text #14

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.0585. Min Act: -0.0000

Data Index: 1453804 (The Pile)

Max Activating Token Index: 390

Text #15

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.0446. Min Act: -0.0000

Data Index: 48918 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1156012 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.1093. Min Act: -0.0000

Data Index: 199366 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1870230 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1092712 (The Pile)

Max Activating Token Index: 103