< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4063 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1899418 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0174. Min Act: -0.0001

Data Index: 135480 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0166. Min Act: -0.0001

Data Index: 103903 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1204794 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1215268 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1560966 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0168. Min Act: -0.0001

Data Index: 496450 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1299188 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0161. Min Act: -0.0001

Data Index: 232150 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0159. Min Act: -0.0001

Data Index: 55094 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0159. Min Act: -0.0001

Data Index: 1206580 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0159. Min Act: -0.0001

Data Index: 649036 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0156. Min Act: -0.0000

Data Index: 491827 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0156. Min Act: -0.0001

Data Index: 717226 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0156. Min Act: -0.0001

Data Index: 457539 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0156. Min Act: -0.0001

Data Index: 447659 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0155. Min Act: -0.0001

Data Index: 64974 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0154. Min Act: -0.0001

Data Index: 506047 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0155. Min Act: -0.0001

Data Index: 938059 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0154. Min Act: -0.0001

Data Index: 332553 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19