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

Dataset: The Pile

Neuron 3937 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.9348. Min Act: -0.0000

Data Index: 13803 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1195317 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1733415 (The Pile)

Max Activating Token Index: 804

Text #3

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1266767 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1944730 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7919. Min Act: -0.0000

Data Index: 886172 (The Pile)

Max Activating Token Index: 832

Text #6

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1775830 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7503. Min Act: -0.0000

Data Index: 613682 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1066214 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7018. Min Act: -0.0000

Data Index: 739625 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1341605 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1365659 (The Pile)

Max Activating Token Index: 160

Text #12

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7019. Min Act: -0.0000

Data Index: 251895 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6769. Min Act: -0.0000

Data Index: 102946 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1151977 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1191347 (The Pile)

Max Activating Token Index: 61

Text #16

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6482. Min Act: -0.0000

Data Index: 848239 (The Pile)

Max Activating Token Index: 733

Text #17

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1746071 (The Pile)

Max Activating Token Index: 349

Text #18

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1335688 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6712. Min Act: -0.0000

Data Index: 792642 (The Pile)

Max Activating Token Index: 410