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

Dataset: The Pile

Neuron 3436 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: 0.6567. Min Range: -0.6567

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1987324 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.6567. Min Act: -0.0000

Data Index: 247257 (The Pile)

Max Activating Token Index: 408

Text #2

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5969. Min Act: -0.0000

Data Index: 724668 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5432. Min Act: -0.0000

Data Index: 884638 (The Pile)

Max Activating Token Index: 42

Text #4

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5095. Min Act: -0.0000

Data Index: 967409 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1661473 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1080219 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5259. Min Act: -0.0000

Data Index: 10084 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1830473 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1395116 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1920641 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1529332 (The Pile)

Max Activating Token Index: 587

Text #12

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5196. Min Act: -0.0000

Data Index: 538916 (The Pile)

Max Activating Token Index: 464

Text #13

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1607934 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4795. Min Act: -0.0000

Data Index: 118209 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1312638 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5227. Min Act: -0.0000

Data Index: 53729 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1816017 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1321668 (The Pile)

Max Activating Token Index: 986

Text #19

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1101054 (The Pile)

Max Activating Token Index: 312