< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4067 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.0649. Min Act: -0.0001

Data Index: 1025914 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.1154. Min Act: -0.0001

Data Index: 88876 (The Pile)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.0720. Min Act: -0.0001

Data Index: 1863715 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.9737. Min Act: -0.0001

Data Index: 695146 (The Pile)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.0376. Min Act: -0.0001

Data Index: 1416836 (The Pile)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.0030. Min Act: -0.0001

Data Index: 869557 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.9273. Min Act: -0.0001

Data Index: 639309 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.0820. Min Act: -0.0001

Data Index: 1199206 (The Pile)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.0473. Min Act: -0.0001

Data Index: 1019409 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.9319. Min Act: -0.0001

Data Index: 1377237 (The Pile)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.0280. Min Act: -0.0001

Data Index: 1123424 (The Pile)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1094261 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8835. Min Act: -0.0001

Data Index: 803301 (The Pile)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8684. Min Act: -0.0001

Data Index: 48788 (The Pile)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.9415. Min Act: -0.0001

Data Index: 1474356 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8803. Min Act: -0.0001

Data Index: 1926404 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8801. Min Act: -0.0001

Data Index: 693391 (The Pile)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.9151. Min Act: -0.0001

Data Index: 1993461 (The Pile)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.9271. Min Act: -0.0001

Data Index: 1925551 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8982. Min Act: -0.0001

Data Index: 1282079 (The Pile)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #19