< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 215 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.6443. Min Range: -2.6443

Max Act: 2.6443. Min Act: -0.0000

Data Index: 1679462 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6443. Min Range: -2.6443

Max Act: 2.4612. Min Act: -0.0000

Data Index: 1243004 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6443. Min Range: -2.6443

Max Act: 2.3128. Min Act: -0.0000

Data Index: 1638500 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6443. Min Range: -2.6443

Max Act: 2.3890. Min Act: -0.0000

Data Index: 72479 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6443. Min Range: -2.6443

Max Act: 2.2770. Min Act: -0.0000

Data Index: 1275953 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6443. Min Range: -2.6443

Max Act: 2.0305. Min Act: -0.0000

Data Index: 692987 (The Pile)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.9623. Min Act: 0.0000

Data Index: 1119149 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6443. Min Range: -2.6443

Max Act: 2.1658. Min Act: -0.0000

Data Index: 840426 (The Pile)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6443. Min Range: -2.6443

Max Act: 2.0183. Min Act: -0.0000

Data Index: 1010510 (The Pile)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.9096. Min Act: -0.0000

Data Index: 282083 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.9994. Min Act: -0.0000

Data Index: 607365 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.9716. Min Act: 0.0000

Data Index: 846525 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.9391. Min Act: -0.0000

Data Index: 475220 (The Pile)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.9594. Min Act: -0.0000

Data Index: 1861603 (The Pile)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.9235. Min Act: -0.0000

Data Index: 1975220 (The Pile)

Max Activating Token Index: 198

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.9146. Min Act: 0.0000

Data Index: 964085 (The Pile)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.8958. Min Act: -0.0000

Data Index: 1858576 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.7648. Min Act: -0.0000

Data Index: 548939 (The Pile)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.9519. Min Act: -0.0000

Data Index: 244006 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6443. Min Range: -2.6443

Max Act: 1.8491. Min Act: -0.0000

Data Index: 1999186 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #19