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

Dataset: The Pile

Neuron 132 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: 1.0127. Min Range: -1.0127

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1206653 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1563845 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1763630 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7392. Min Act: -0.0000

Data Index: 411582 (The Pile)

Max Activating Token Index: 743

Text #4

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6004. Min Act: -0.0000

Data Index: 944674 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6623. Min Act: 0.0000

Data Index: 1842565 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6241. Min Act: -0.0000

Data Index: 934691 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1176928 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1349276 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1218882 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6495. Min Act: -0.0000

Data Index: 7337 (The Pile)

Max Activating Token Index: 360

Text #11

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1178877 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1587892 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6236. Min Act: 0.0000

Data Index: 1501044 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1000256 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1844438 (The Pile)

Max Activating Token Index: 91

Text #16

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1782752 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1298050 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6410. Min Act: -0.0000

Data Index: 803990 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1029010 (The Pile)

Max Activating Token Index: 828