< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5096 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4751. Min Act: -0.0000

Data Index: 341192 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4769. Min Act: 0.0000

Data Index: 860502 (The Pile)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4337. Min Act: -0.0000

Data Index: 511257 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4330. Min Act: 0.0000

Data Index: 824128 (The Pile)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4603. Min Act: 0.0000

Data Index: 1545244 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4017. Min Act: 0.0000

Data Index: 808851 (The Pile)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1909556 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4233. Min Act: 0.0000

Data Index: 1119363 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4158. Min Act: 0.0000

Data Index: 761232 (The Pile)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4088. Min Act: 0.0000

Data Index: 780979 (The Pile)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4278. Min Act: 0.0000

Data Index: 1282971 (The Pile)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4027. Min Act: 0.0000

Data Index: 1871486 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3971. Min Act: -0.0000

Data Index: 556875 (The Pile)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4076. Min Act: 0.0000

Data Index: 853629 (The Pile)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4082. Min Act: -0.0000

Data Index: 522585 (The Pile)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4019. Min Act: 0.0000

Data Index: 918390 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4038. Min Act: 0.0000

Data Index: 264092 (The Pile)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3734. Min Act: 0.0000

Data Index: 180183 (The Pile)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1195164 (The Pile)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3955. Min Act: 0.0000

Data Index: 408011 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #19