< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 65 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.0575. Min Range: -1.0575

Max Act: 1.0575. Min Act: -0.0004

Data Index: 28373 (The Pile)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0575. Min Range: -1.0575

Max Act: 1.0138. Min Act: -0.0004

Data Index: 93764 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9485. Min Act: -0.0004

Data Index: 1856469 (The Pile)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9747. Min Act: -0.0004

Data Index: 911984 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9655. Min Act: -0.0004

Data Index: 1748726 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9690. Min Act: -0.0004

Data Index: 1088558 (The Pile)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9627. Min Act: -0.0004

Data Index: 1755327 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.8894. Min Act: -0.0004

Data Index: 1183648 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9186. Min Act: -0.0004

Data Index: 265458 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9138. Min Act: -0.0004

Data Index: 1754878 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9320. Min Act: -0.0004

Data Index: 1262880 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9515. Min Act: -0.0004

Data Index: 1676345 (The Pile)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.8624. Min Act: -0.0004

Data Index: 463145 (The Pile)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9148. Min Act: -0.0004

Data Index: 1998838 (The Pile)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.8795. Min Act: -0.0004

Data Index: 1309699 (The Pile)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.8767. Min Act: -0.0004

Data Index: 341495 (The Pile)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9038. Min Act: -0.0004

Data Index: 747949 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.8778. Min Act: -0.0004

Data Index: 1071401 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.8735. Min Act: -0.0004

Data Index: 444752 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.8715. Min Act: -0.0004

Data Index: 1189789 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #19