< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 2034 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3529. Min Act: 0.0000

Data Index: 1474460 (The Pile)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3191. Min Act: 0.0000

Data Index: 766789 (The Pile)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3272. Min Act: -0.0001

Data Index: 837583 (The Pile)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3092. Min Act: -0.0001

Data Index: 177090 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3196. Min Act: -0.0001

Data Index: 466007 (The Pile)

Max Activating Token Index: 422

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3330. Min Act: -0.0001

Data Index: 351513 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3291. Min Act: -0.0001

Data Index: 495682 (The Pile)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2994. Min Act: -0.0001

Data Index: 130815 (The Pile)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2979. Min Act: -0.0001

Data Index: 971640 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2974. Min Act: 0.0000

Data Index: 684643 (The Pile)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2965. Min Act: 0.0000

Data Index: 1889946 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2914. Min Act: -0.0001

Data Index: 223691 (The Pile)

Max Activating Token Index: 680

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2935. Min Act: 0.0000

Data Index: 38118 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2919. Min Act: -0.0000

Data Index: 236061 (The Pile)

Max Activating Token Index: 198

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3039. Min Act: -0.0001

Data Index: 154474 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2760. Min Act: 0.0000

Data Index: 316420 (The Pile)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2771. Min Act: -0.0001

Data Index: 1897375 (The Pile)

Max Activating Token Index: 151

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2724. Min Act: -0.0001

Data Index: 1205059 (The Pile)

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2838. Min Act: -0.0001

Data Index: 1383686 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2893. Min Act: -0.0001

Data Index: 1561248 (The Pile)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #19