< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 34 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.6013. Min Act: -0.0001

Data Index: 44737 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.6233. Min Act: -0.0001

Data Index: 216375 (The Pile)

Max Activating Token Index: 712

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.5735. Min Act: -0.0001

Data Index: 236563 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.4771. Min Act: -0.0001

Data Index: 1243733 (The Pile)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.4579. Min Act: -0.0001

Data Index: 1216044 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3824. Min Act: -0.0001

Data Index: 1943632 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3882. Min Act: -0.0001

Data Index: 1224682 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3852. Min Act: -0.0001

Data Index: 1653203 (The Pile)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.4091. Min Act: -0.0001

Data Index: 1262096 (The Pile)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3730. Min Act: -0.0001

Data Index: 1389108 (The Pile)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3357. Min Act: -0.0001

Data Index: 1052116 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2793. Min Act: -0.0001

Data Index: 222931 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3181. Min Act: -0.0001

Data Index: 1276620 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3298. Min Act: -0.0001

Data Index: 1976020 (The Pile)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2594. Min Act: -0.0001

Data Index: 107060 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3035. Min Act: -0.0001

Data Index: 319871 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3108. Min Act: -0.0001

Data Index: 298170 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2989. Min Act: -0.0001

Data Index: 968245 (The Pile)

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3156. Min Act: -0.0001

Data Index: 1871874 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3645. Min Act: -0.0001

Data Index: 1370289 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #19