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

Dataset: The Pile

Neuron 1612 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1700217 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1094253 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 1.1819. Min Range: -1.1819

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1776686 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1564133 (The Pile)

Max Activating Token Index: 440

Text #4

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1137759 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1033433 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1254806 (The Pile)

Max Activating Token Index: 827

Text #7

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8427. Min Act: -0.0000

Data Index: 3658 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1044802 (The Pile)

Max Activating Token Index: 774

Text #9

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8580. Min Act: -0.0000

Data Index: 215157 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1459946 (The Pile)

Max Activating Token Index: 28

Text #11

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1807964 (The Pile)

Max Activating Token Index: 792

Text #12

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1403066 (The Pile)

Max Activating Token Index: 509

Text #13

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8361. Min Act: -0.0000

Data Index: 604632 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7809. Min Act: -0.0000

Data Index: 356028 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8174. Min Act: -0.0000

Data Index: 514086 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1022670 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.8877. Min Act: -0.0000

Data Index: 774487 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7994. Min Act: -0.0000

Data Index: 420992 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 1.1819. Min Range: -1.1819

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1602073 (The Pile)

Max Activating Token Index: 602