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

Dataset: The Pile

Neuron 4804 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3650. Min Act: -0.0000

Data Index: 25586 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1823011 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1304396 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1438579 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3223. Min Act: -0.0000

Data Index: 924217 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3179. Min Act: -0.0000

Data Index: 664257 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1753311 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3116. Min Act: -0.0000

Data Index: 817276 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2971. Min Act: -0.0000

Data Index: 128104 (The Pile)

Max Activating Token Index: 968

Text #9

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1390371 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1239431 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1131325 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1525313 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2926. Min Act: -0.0000

Data Index: 979269 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2929. Min Act: -0.0000

Data Index: 404300 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2670. Min Act: -0.0000

Data Index: 245984 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2925. Min Act: -0.0000

Data Index: 358593 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2924. Min Act: -0.0000

Data Index: 981250 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1534966 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1063086 (The Pile)

Max Activating Token Index: 394