< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2331 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.5375. Min Act: -0.0002

Data Index: 77026 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.5062. Min Act: -0.0002

Data Index: 1957953 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4840. Min Act: -0.0002

Data Index: 1125300 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4668. Min Act: -0.0002

Data Index: 1984039 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4531. Min Act: -0.0002

Data Index: 1535757 (The Pile)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4634. Min Act: -0.0002

Data Index: 1433330 (The Pile)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4571. Min Act: -0.0002

Data Index: 1893971 (The Pile)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4357. Min Act: -0.0002

Data Index: 907947 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4304. Min Act: -0.0002

Data Index: 1452478 (The Pile)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4130. Min Act: -0.0002

Data Index: 1930391 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4196. Min Act: -0.0002

Data Index: 223453 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4047. Min Act: -0.0002

Data Index: 309051 (The Pile)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4250. Min Act: -0.0002

Data Index: 1236647 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4124. Min Act: -0.0002

Data Index: 1957208 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4099. Min Act: -0.0002

Data Index: 206093 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4030. Min Act: -0.0002

Data Index: 78417 (The Pile)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4108. Min Act: -0.0002

Data Index: 266565 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3924. Min Act: -0.0002

Data Index: 810251 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3917. Min Act: -0.0002

Data Index: 988795 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3889. Min Act: -0.0002

Data Index: 1655928 (The Pile)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #19