< Prev | Home | Model | Random | Next >

Model: SoLU Model: 1 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 29 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-1l-pile')



Text #0

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1198. Min Act: -0.0002

Data Index: 1892106 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1049. Min Act: -0.0002

Data Index: 403318 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1949573 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0977. Min Act: -0.0002

Data Index: 379199 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1399955 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0946. Min Act: -0.0002

Data Index: 504091 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1161689 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0902. Min Act: -0.0002

Data Index: 157161 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1457320 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1500676 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1951968 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1051774 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0856. Min Act: -0.0002

Data Index: 400270 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0846. Min Act: -0.0002

Data Index: 237520 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0845. Min Act: -0.0002

Data Index: 52764 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1297096 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1282236 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0828. Min Act: -0.0002

Data Index: 178628 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1389342 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0822. Min Act: -0.0002

Data Index: 741292 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #19