< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5097 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: 3.3162. Min Range: -3.3162

Max Act: 3.3162. Min Act: -0.0000

Data Index: 1551778 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.6936. Min Act: -0.0000

Data Index: 1153123 (The Pile)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.7876. Min Act: -0.0000

Data Index: 1094653 (The Pile)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.8998. Min Act: -0.0000

Data Index: 1817768 (The Pile)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.3673. Min Act: -0.0000

Data Index: 193622 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.3713. Min Act: -0.0000

Data Index: 1113109 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.5772. Min Act: -0.0000

Data Index: 415584 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.3840. Min Act: -0.0000

Data Index: 1641086 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.7399. Min Act: -0.0000

Data Index: 1368410 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.3246. Min Act: -0.0000

Data Index: 1807824 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.3968. Min Act: -0.0000

Data Index: 1791173 (The Pile)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.5070. Min Act: -0.0000

Data Index: 857615 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.4374. Min Act: -0.0000

Data Index: 1893974 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.1916. Min Act: -0.0000

Data Index: 532469 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.3221. Min Act: -0.0000

Data Index: 1838567 (The Pile)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.2864. Min Act: -0.0000

Data Index: 1905064 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.3025. Min Act: -0.0000

Data Index: 703788 (The Pile)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.2658. Min Act: -0.0000

Data Index: 448193 (The Pile)

Max Activating Token Index: 583

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.0594. Min Act: -0.0000

Data Index: 1549400 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.3162. Min Range: -3.3162

Max Act: 2.1486. Min Act: -0.0000

Data Index: 1747144 (The Pile)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #19