< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4036 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.3948. Min Act: -0.0001

Data Index: 417282 (The Pile)

Max Activating Token Index: 936

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.6816. Min Act: -0.0001

Data Index: 1148793 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.5448. Min Act: -0.0001

Data Index: 326243 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.5153. Min Act: -0.0001

Data Index: 1966819 (The Pile)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.4007. Min Act: -0.0001

Data Index: 914140 (The Pile)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.4696. Min Act: -0.0001

Data Index: 709932 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.4733. Min Act: -0.0001

Data Index: 204296 (The Pile)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.3400. Min Act: -0.0001

Data Index: 1243204 (The Pile)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.4913. Min Act: -0.0001

Data Index: 1327854 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.4787. Min Act: -0.0001

Data Index: 754638 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.4138. Min Act: -0.0001

Data Index: 51994 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.3988. Min Act: -0.0001

Data Index: 1908346 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.5982. Min Act: -0.0001

Data Index: 716667 (The Pile)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.4273. Min Act: -0.0001

Data Index: 1531364 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.4208. Min Act: -0.0001

Data Index: 1665393 (The Pile)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.4848. Min Act: -0.0001

Data Index: 854739 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.3133. Min Act: -0.0001

Data Index: 1616832 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.4627. Min Act: -0.0001

Data Index: 140763 (The Pile)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.3513. Min Act: -0.0001

Data Index: 105993 (The Pile)

Max Activating Token Index: 296

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6816. Min Range: -1.6816

Max Act: 1.2267. Min Act: -0.0001

Data Index: 860077 (The Pile)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #19