< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.9026. Min Act: -0.0000

Data Index: 1778842 (The Pile)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.8641. Min Act: -0.0000

Data Index: 324568 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.5190. Min Act: -0.0000

Data Index: 793487 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.4814. Min Act: -0.0000

Data Index: 1835171 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.7079. Min Act: -0.0000

Data Index: 1949573 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.4519. Min Act: -0.0000

Data Index: 718597 (The Pile)

Max Activating Token Index: 98

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.6969. Min Act: -0.0000

Data Index: 903649 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.2961. Min Act: -0.0000

Data Index: 1910391 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.5956. Min Act: -0.0000

Data Index: 1941754 (The Pile)

Max Activating Token Index: 346

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.5806. Min Act: -0.0000

Data Index: 539945 (The Pile)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.4845. Min Act: -0.0000

Data Index: 786916 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.3021. Min Act: -0.0000

Data Index: 186929 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.4329. Min Act: -0.0000

Data Index: 137634 (The Pile)

Max Activating Token Index: 99

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.5229. Min Act: -0.0000

Data Index: 664922 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.6519. Min Act: -0.0000

Data Index: 156599 (The Pile)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.2528. Min Act: -0.0000

Data Index: 1553007 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.3906. Min Act: -0.0000

Data Index: 1273819 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.2450. Min Act: -0.0000

Data Index: 1037298 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.1143. Min Act: -0.0000

Data Index: 548264 (The Pile)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9026. Min Range: -2.9026

Max Act: 2.3388. Min Act: -0.0000

Data Index: 1128697 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #19