< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3052 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.6810. Min Act: -0.0000

Data Index: 1270887 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.6198. Min Act: -0.0001

Data Index: 1429549 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.5500. Min Act: -0.0001

Data Index: 1725398 (The Pile)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4371. Min Act: -0.0000

Data Index: 63914 (The Pile)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4247. Min Act: -0.0001

Data Index: 79012 (The Pile)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4131. Min Act: -0.0001

Data Index: 555212 (The Pile)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4029. Min Act: -0.0001

Data Index: 219288 (The Pile)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.4096. Min Act: -0.0001

Data Index: 160905 (The Pile)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.3351. Min Act: -0.0000

Data Index: 129433 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.3539. Min Act: -0.0001

Data Index: 1083052 (The Pile)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.3048. Min Act: -0.0001

Data Index: 1762582 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1238887 (The Pile)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.2566. Min Act: -0.0001

Data Index: 236803 (The Pile)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1964707 (The Pile)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1869172 (The Pile)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1428955 (The Pile)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.2898. Min Act: -0.0001

Data Index: 1237338 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.2720. Min Act: -0.0000

Data Index: 1364030 (The Pile)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.3290. Min Act: -0.0000

Data Index: 383754 (The Pile)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6810. Min Range: -1.6810

Max Act: 1.2610. Min Act: -0.0001

Data Index: 983274 (The Pile)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #19