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

Dataset: The Pile

Neuron 1181 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5963. Min Act: -0.0000

Data Index: 333564 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1975790 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5573. Min Act: -0.0000

Data Index: 203386 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1478255 (The Pile)

Max Activating Token Index: 46

Text #4

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1965383 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5052. Min Act: -0.0000

Data Index: 600586 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1118686 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1915073 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1578164 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4707. Min Act: -0.0000

Data Index: 630034 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1709750 (The Pile)

Max Activating Token Index: 923

Text #11

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4441. Min Act: -0.0000

Data Index: 804216 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1827698 (The Pile)

Max Activating Token Index: 251

Text #13

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1833075 (The Pile)

Max Activating Token Index: 136

Text #14

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4402. Min Act: -0.0000

Data Index: 296480 (The Pile)

Max Activating Token Index: 158

Text #15

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4336. Min Act: -0.0000

Data Index: 893725 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4047. Min Act: -0.0000

Data Index: 480530 (The Pile)

Max Activating Token Index: 889

Text #17

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4286. Min Act: -0.0000

Data Index: 592742 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4242. Min Act: -0.0000

Data Index: 183765 (The Pile)

Max Activating Token Index: 962

Text #19

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4416. Min Act: -0.0000

Data Index: 36685 (The Pile)

Max Activating Token Index: 1004