< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 64 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.8438. Min Act: -0.0001

Data Index: 1919094 (The Pile)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7954. Min Act: -0.0001

Data Index: 493365 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7335. Min Act: -0.0001

Data Index: 1435856 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6979. Min Act: -0.0001

Data Index: 205247 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7040. Min Act: -0.0001

Data Index: 1746013 (The Pile)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6799. Min Act: -0.0001

Data Index: 1713051 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6367. Min Act: -0.0001

Data Index: 1037156 (The Pile)

Max Activating Token Index: 98

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6537. Min Act: -0.0001

Data Index: 1252824 (The Pile)

Max Activating Token Index: 60

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6320. Min Act: -0.0001

Data Index: 1130033 (The Pile)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6548. Min Act: -0.0001

Data Index: 23868 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6718. Min Act: -0.0001

Data Index: 1446151 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6705. Min Act: -0.0001

Data Index: 33273 (The Pile)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6323. Min Act: -0.0001

Data Index: 126042 (The Pile)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6270. Min Act: -0.0001

Data Index: 1867730 (The Pile)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6166. Min Act: -0.0001

Data Index: 194533 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6704. Min Act: -0.0001

Data Index: 928042 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6532. Min Act: -0.0001

Data Index: 234185 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6283. Min Act: -0.0001

Data Index: 1115239 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6129. Min Act: -0.0001

Data Index: 1978304 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6304. Min Act: -0.0001

Data Index: 233195 (The Pile)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #19