< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 37 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.3238. Min Act: -0.0000

Data Index: 1873048 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.2636. Min Act: -0.0000

Data Index: 20022 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.0934. Min Act: -0.0000

Data Index: 1057357 (The Pile)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.0946. Min Act: -0.0000

Data Index: 104867 (The Pile)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1132036 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.0820. Min Act: -0.0000

Data Index: 216732 (The Pile)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.1132. Min Act: -0.0000

Data Index: 81228 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1647285 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.1132. Min Act: -0.0000

Data Index: 560906 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.1253. Min Act: -0.0000

Data Index: 1350230 (The Pile)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1771182 (The Pile)

Max Activating Token Index: 884

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.0052. Min Act: -0.0000

Data Index: 764076 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.0131. Min Act: -0.0000

Data Index: 801889 (The Pile)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.3238. Min Range: -1.3238

Max Act: 1.0143. Min Act: -0.0000

Data Index: 227852 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.3238. Min Range: -1.3238

Max Act: 0.9777. Min Act: -0.0000

Data Index: 406029 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.3238. Min Range: -1.3238

Max Act: 0.9606. Min Act: -0.0000

Data Index: 137770 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.3238. Min Range: -1.3238

Max Act: 0.9953. Min Act: 0.0000

Data Index: 996083 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.3238. Min Range: -1.3238

Max Act: 0.9878. Min Act: -0.0000

Data Index: 322557 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.3238. Min Range: -1.3238

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1438014 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.3238. Min Range: -1.3238

Max Act: 0.9525. Min Act: 0.0000

Data Index: 440828 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #19