< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4034 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: 1.0714. Min Range: -1.0714

Max Act: 1.0714. Min Act: -0.0001

Data Index: 1043417 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0232. Min Act: -0.0001

Data Index: 1679316 (The Pile)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9590. Min Act: -0.0001

Data Index: 366979 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9906. Min Act: -0.0001

Data Index: 339031 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0667. Min Act: -0.0001

Data Index: 431490 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9687. Min Act: -0.0001

Data Index: 1290383 (The Pile)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9375. Min Act: -0.0001

Data Index: 313070 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0163. Min Act: -0.0001

Data Index: 177183 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8881. Min Act: -0.0001

Data Index: 1328568 (The Pile)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9518. Min Act: -0.0001

Data Index: 214165 (The Pile)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.7978. Min Act: -0.0001

Data Index: 1887748 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8565. Min Act: -0.0001

Data Index: 1175893 (The Pile)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8658. Min Act: -0.0001

Data Index: 375755 (The Pile)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8744. Min Act: -0.0001

Data Index: 1735916 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8756. Min Act: -0.0001

Data Index: 820743 (The Pile)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8545. Min Act: -0.0001

Data Index: 1702480 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9155. Min Act: -0.0001

Data Index: 1076802 (The Pile)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8526. Min Act: -0.0001

Data Index: 1342529 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8732. Min Act: -0.0001

Data Index: 1221037 (The Pile)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8443. Min Act: -0.0001

Data Index: 1661686 (The Pile)

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #19