Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 0 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.9524. Min Act: -0.0000

Data Index: 82672 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.9302. Min Act: -0.0000

Data Index: 196557 (The Pile)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.6561. Min Act: -0.0000

Data Index: 747990 (The Pile)

Max Activating Token Index: 291

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.9162. Min Act: -0.0000

Data Index: 1529048 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.6943. Min Act: -0.0000

Data Index: 1372861 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.4895. Min Act: -0.0000

Data Index: 1177329 (The Pile)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.7425. Min Act: -0.0000

Data Index: 347239 (The Pile)

Max Activating Token Index: 713

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.5225. Min Act: -0.0000

Data Index: 219997 (The Pile)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.4875. Min Act: -0.0000

Data Index: 534870 (The Pile)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.1026. Min Act: -0.0000

Data Index: 922403 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.3793. Min Act: -0.0000

Data Index: 1425756 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.2568. Min Act: -0.0000

Data Index: 1148485 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.4340. Min Act: -0.0000

Data Index: 1495702 (The Pile)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.3395. Min Act: -0.0000

Data Index: 1375294 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.3310. Min Act: -0.0000

Data Index: 1936670 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.3160. Min Act: -0.0000

Data Index: 767274 (The Pile)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.2016. Min Act: -0.0000

Data Index: 1306933 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.1664. Min Act: -0.0000

Data Index: 901054 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.2442. Min Act: -0.0000

Data Index: 1795339 (The Pile)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9524. Min Range: -2.9524

Max Act: 2.3031. Min Act: -0.0000

Data Index: 634115 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #19