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

Dataset: The Pile

Neuron 2085 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5636. Min Act: -0.0000

Data Index: 499078 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5717. Min Act: -0.0001

Data Index: 1939493 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1245058 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4214. Min Act: -0.0000

Data Index: 854305 (The Pile)

Max Activating Token Index: 829

Text #4

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4040. Min Act: -0.0000

Data Index: 652826 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4478. Min Act: -0.0000

Data Index: 78691 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4141. Min Act: -0.0000

Data Index: 798112 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1581274 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1860372 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1991077 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1514793 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4271. Min Act: -0.0000

Data Index: 125055 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3510. Min Act: -0.0000

Data Index: 595904 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3355. Min Act: -0.0000

Data Index: 153512 (The Pile)

Max Activating Token Index: 871

Text #14

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3672. Min Act: -0.0000

Data Index: 524431 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1370819 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1936637 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3793. Min Act: -0.0000

Data Index: 760073 (The Pile)

Max Activating Token Index: 769

Text #18

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1327113 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1930833 (The Pile)

Max Activating Token Index: 647