< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 72 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.4411. Min Act: -0.0001

Data Index: 803549 (The Pile)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.3538. Min Act: -0.0001

Data Index: 539774 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.3503. Min Act: -0.0001

Data Index: 289473 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.1765. Min Act: -0.0001

Data Index: 8875 (The Pile)

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.0618. Min Act: -0.0001

Data Index: 782263 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.1531. Min Act: -0.0001

Data Index: 1909565 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.1276. Min Act: -0.0001

Data Index: 900387 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.1002. Min Act: -0.0001

Data Index: 113630 (The Pile)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.4411. Min Range: -2.4411

Max Act: 1.9902. Min Act: -0.0001

Data Index: 1188460 (The Pile)

Max Activating Token Index: 371

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.1145. Min Act: -0.0001

Data Index: 175968 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.4411. Min Range: -2.4411

Max Act: 1.9811. Min Act: -0.0001

Data Index: 518365 (The Pile)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.0123. Min Act: -0.0001

Data Index: 1162671 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.4411. Min Range: -2.4411

Max Act: 1.9009. Min Act: -0.0001

Data Index: 1300274 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.4411. Min Range: -2.4411

Max Act: 1.9925. Min Act: -0.0001

Data Index: 1006705 (The Pile)

Max Activating Token Index: 731

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.4411. Min Range: -2.4411

Max Act: 2.2517. Min Act: -0.0001

Data Index: 763532 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.4411. Min Range: -2.4411

Max Act: 1.9026. Min Act: -0.0001

Data Index: 1356276 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.4411. Min Range: -2.4411

Max Act: 1.8355. Min Act: -0.0001

Data Index: 445582 (The Pile)

Max Activating Token Index: 456

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.4411. Min Range: -2.4411

Max Act: 1.9048. Min Act: -0.0001

Data Index: 1888567 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.4411. Min Range: -2.4411

Max Act: 1.7817. Min Act: -0.0001

Data Index: 161848 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.4411. Min Range: -2.4411

Max Act: 1.7800. Min Act: -0.0001

Data Index: 1651172 (The Pile)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #19