< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 35 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: 0.6799. Min Range: -0.6799

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1306009 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6532. Min Act: -0.0001

Data Index: 1112086 (The Pile)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6657. Min Act: -0.0001

Data Index: 1153465 (The Pile)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6575. Min Act: -0.0001

Data Index: 1730137 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6357. Min Act: -0.0001

Data Index: 1151178 (The Pile)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6434. Min Act: -0.0001

Data Index: 1443782 (The Pile)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6799. Min Act: -0.0001

Data Index: 386010 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6746. Min Act: -0.0001

Data Index: 162915 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6277. Min Act: -0.0001

Data Index: 712002 (The Pile)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6606. Min Act: -0.0001

Data Index: 138120 (The Pile)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5648. Min Act: -0.0001

Data Index: 1146061 (The Pile)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6236. Min Act: -0.0001

Data Index: 449598 (The Pile)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6191. Min Act: -0.0001

Data Index: 922515 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6456. Min Act: -0.0001

Data Index: 1476718 (The Pile)

Max Activating Token Index: 461

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6108. Min Act: -0.0001

Data Index: 500493 (The Pile)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6100. Min Act: -0.0001

Data Index: 1208042 (The Pile)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6048. Min Act: -0.0001

Data Index: 719481 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6333. Min Act: -0.0001

Data Index: 1364843 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6039. Min Act: -0.0001

Data Index: 1679251 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6093. Min Act: -0.0001

Data Index: 221710 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #19