< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 35 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: 0.4880. Min Range: -0.4880

Max Act: 0.4880. Min Act: -0.0001

Data Index: 235680 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4231. Min Act: -0.0001

Data Index: 1532930 (The Pile)

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4334. Min Act: -0.0001

Data Index: 31411 (The Pile)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4271. Min Act: -0.0001

Data Index: 837746 (The Pile)

Max Activating Token Index: 290

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4408. Min Act: -0.0000

Data Index: 304190 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4223. Min Act: -0.0001

Data Index: 659579 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4017. Min Act: -0.0001

Data Index: 1632871 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4132. Min Act: -0.0001

Data Index: 638078 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4064. Min Act: -0.0001

Data Index: 280293 (The Pile)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4143. Min Act: -0.0001

Data Index: 294392 (The Pile)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4195. Min Act: -0.0001

Data Index: 1817840 (The Pile)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4395. Min Act: -0.0001

Data Index: 1116240 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3981. Min Act: -0.0001

Data Index: 153781 (The Pile)

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3906. Min Act: -0.0001

Data Index: 367118 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4112. Min Act: -0.0001

Data Index: 626614 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4193. Min Act: -0.0001

Data Index: 1393269 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4055. Min Act: -0.0001

Data Index: 1130111 (The Pile)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3626. Min Act: -0.0001

Data Index: 192718 (The Pile)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3874. Min Act: -0.0001

Data Index: 213347 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3795. Min Act: -0.0001

Data Index: 268424 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #19