< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.4731. Min Act: -0.0001

Data Index: 391210 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3994. Min Act: -0.0001

Data Index: 1418200 (The Pile)

Max Activating Token Index: 639

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.4434. Min Act: -0.0001

Data Index: 1905 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3605. Min Act: -0.0001

Data Index: 883635 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3263. Min Act: -0.0001

Data Index: 535260 (The Pile)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3433. Min Act: -0.0001

Data Index: 1216151 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.4080. Min Act: -0.0001

Data Index: 1098331 (The Pile)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3717. Min Act: -0.0001

Data Index: 1553613 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3114. Min Act: -0.0001

Data Index: 61192 (The Pile)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3017. Min Act: -0.0001

Data Index: 598992 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3268. Min Act: -0.0001

Data Index: 1797484 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3304. Min Act: -0.0001

Data Index: 1555791 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3170. Min Act: -0.0001

Data Index: 1661486 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3172. Min Act: -0.0001

Data Index: 1710703 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3184. Min Act: -0.0001

Data Index: 498280 (The Pile)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.2724. Min Act: -0.0001

Data Index: 321750 (The Pile)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3389. Min Act: -0.0001

Data Index: 1508841 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3072. Min Act: -0.0001

Data Index: 917822 (The Pile)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.2632. Min Act: -0.0001

Data Index: 1692685 (The Pile)

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3409. Min Act: -0.0001

Data Index: 1179429 (The Pile)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #19