< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3065 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.4632. Min Act: -0.0002

Data Index: 1063257 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.4372. Min Act: -0.0002

Data Index: 1222666 (The Pile)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.4335. Min Act: -0.0002

Data Index: 1619040 (The Pile)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3973. Min Act: -0.0002

Data Index: 1032655 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3907. Min Act: -0.0002

Data Index: 328455 (The Pile)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3651. Min Act: -0.0002

Data Index: 302015 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3243. Min Act: -0.0002

Data Index: 494575 (The Pile)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2521. Min Act: -0.0002

Data Index: 1638816 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2990. Min Act: -0.0002

Data Index: 374767 (The Pile)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2878. Min Act: -0.0002

Data Index: 1243581 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2871. Min Act: -0.0002

Data Index: 423804 (The Pile)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3094. Min Act: -0.0002

Data Index: 543439 (The Pile)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3113. Min Act: -0.0002

Data Index: 1844151 (The Pile)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2927. Min Act: -0.0002

Data Index: 1134363 (The Pile)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2586. Min Act: -0.0002

Data Index: 622042 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2516. Min Act: -0.0002

Data Index: 574965 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2466. Min Act: -0.0002

Data Index: 1949959 (The Pile)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2146. Min Act: -0.0002

Data Index: 1335262 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2764. Min Act: -0.0002

Data Index: 1176996 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2035. Min Act: -0.0002

Data Index: 660206 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #19