< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4033 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4369. Min Act: -0.0001

Data Index: 1435973 (The Pile)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1195188 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3706. Min Act: -0.0000

Data Index: 121799 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3753. Min Act: -0.0000

Data Index: 965013 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3644. Min Act: -0.0000

Data Index: 324465 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3653. Min Act: -0.0001

Data Index: 892626 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3619. Min Act: -0.0001

Data Index: 757815 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3590. Min Act: -0.0001

Data Index: 1973220 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1806278 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3504. Min Act: -0.0000

Data Index: 990559 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3425. Min Act: -0.0000

Data Index: 383338 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3625. Min Act: -0.0001

Data Index: 1493293 (The Pile)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3477. Min Act: -0.0001

Data Index: 766941 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3474. Min Act: -0.0001

Data Index: 1996874 (The Pile)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3588. Min Act: -0.0001

Data Index: 1317308 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3448. Min Act: -0.0001

Data Index: 871521 (The Pile)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3431. Min Act: -0.0000

Data Index: 59466 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3306. Min Act: -0.0001

Data Index: 1672157 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1693415 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3241. Min Act: -0.0001

Data Index: 833007 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #19