< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 61 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6951. Min Act: -0.0001

Data Index: 245782 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6884. Min Act: -0.0001

Data Index: 1351952 (The Pile)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6205. Min Act: -0.0001

Data Index: 1580447 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5728. Min Act: -0.0001

Data Index: 282973 (The Pile)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6255. Min Act: -0.0001

Data Index: 1950009 (The Pile)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5972. Min Act: -0.0001

Data Index: 1572725 (The Pile)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5507. Min Act: -0.0001

Data Index: 1567968 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5422. Min Act: -0.0001

Data Index: 983688 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5173. Min Act: -0.0001

Data Index: 822858 (The Pile)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5918. Min Act: -0.0001

Data Index: 5453 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5270. Min Act: -0.0001

Data Index: 1984455 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5293. Min Act: -0.0001

Data Index: 859713 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4953. Min Act: -0.0001

Data Index: 1008901 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5198. Min Act: -0.0001

Data Index: 1010997 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5726. Min Act: -0.0001

Data Index: 55572 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5384. Min Act: -0.0001

Data Index: 1535209 (The Pile)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5378. Min Act: -0.0001

Data Index: 1861784 (The Pile)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5327. Min Act: -0.0001

Data Index: 1894289 (The Pile)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4961. Min Act: -0.0001

Data Index: 775519 (The Pile)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5364. Min Act: -0.0001

Data Index: 1052731 (The Pile)

Max Activating Token Index: 549

Click toggle to see full text

Truncated

Full Text #19