< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 69 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.8922. Min Act: -0.0001

Data Index: 1967258 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.9102. Min Act: -0.0001

Data Index: 40178 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7880. Min Act: -0.0001

Data Index: 22165 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.8058. Min Act: -0.0001

Data Index: 1658669 (The Pile)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7837. Min Act: -0.0001

Data Index: 1148037 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7471. Min Act: -0.0001

Data Index: 956706 (The Pile)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.8379. Min Act: -0.0001

Data Index: 391883 (The Pile)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7221. Min Act: -0.0001

Data Index: 168207 (The Pile)

Max Activating Token Index: 907

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7979. Min Act: -0.0001

Data Index: 645912 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7156. Min Act: -0.0001

Data Index: 1763844 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7023. Min Act: -0.0001

Data Index: 179305 (The Pile)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6588. Min Act: -0.0001

Data Index: 1504621 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7291. Min Act: -0.0001

Data Index: 1757891 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6757. Min Act: -0.0001

Data Index: 548182 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7544. Min Act: -0.0001

Data Index: 1423823 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6712. Min Act: -0.0001

Data Index: 147457 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7203. Min Act: -0.0001

Data Index: 821352 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7140. Min Act: -0.0001

Data Index: 184786 (The Pile)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6912. Min Act: -0.0001

Data Index: 221939 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7394. Min Act: -0.0001

Data Index: 1359683 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #19