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

Dataset: The Pile

Neuron 2 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5917. Min Act: -0.0000

Data Index: 862769 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1921567 (The Pile)

Max Activating Token Index: 663

Text #2

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1678146 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5699. Min Act: -0.0000

Data Index: 138763 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1051971 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4973. Min Act: -0.0000

Data Index: 354324 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1570864 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5138. Min Act: -0.0000

Data Index: 623693 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4923. Min Act: -0.0000

Data Index: 971054 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5107. Min Act: -0.0000

Data Index: 646286 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4985. Min Act: -0.0001

Data Index: 319951 (The Pile)

Max Activating Token Index: 421

Text #11

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5173. Min Act: -0.0000

Data Index: 346351 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1130387 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1248915 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5223. Min Act: -0.0000

Data Index: 845002 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1439658 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4946. Min Act: -0.0000

Data Index: 387549 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1345847 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1460820 (The Pile)

Max Activating Token Index: 183

Text #19

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4587. Min Act: -0.0000

Data Index: 260315 (The Pile)

Max Activating Token Index: 635