< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 48 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: 0.8080. Min Range: -0.8080

Max Act: 0.7853. Min Act: -0.0001

Data Index: 1029103 (The Pile)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.8080. Min Act: -0.0001

Data Index: 1115766 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1474484 (The Pile)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7324. Min Act: -0.0001

Data Index: 835305 (The Pile)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7257. Min Act: -0.0001

Data Index: 801287 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7326. Min Act: -0.0001

Data Index: 416617 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6390. Min Act: -0.0001

Data Index: 1659981 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7126. Min Act: -0.0001

Data Index: 385056 (The Pile)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7202. Min Act: -0.0001

Data Index: 988662 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5744. Min Act: -0.0001

Data Index: 1303185 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6192. Min Act: -0.0001

Data Index: 694538 (The Pile)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5991. Min Act: -0.0001

Data Index: 1438634 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5856. Min Act: -0.0001

Data Index: 1362251 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5560. Min Act: -0.0001

Data Index: 446162 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6042. Min Act: -0.0001

Data Index: 627352 (The Pile)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5634. Min Act: -0.0001

Data Index: 290478 (The Pile)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5407. Min Act: -0.0001

Data Index: 297428 (The Pile)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1386606 (The Pile)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5481. Min Act: -0.0001

Data Index: 394589 (The Pile)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5774. Min Act: -0.0001

Data Index: 777520 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #19