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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 848 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0090. Min Range: -1.0090

Max Act: 1.0090. Min Act: -0.0002

Data Index: 11300 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9227. Min Act: -0.0002

Data Index: 626113 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8665. Min Act: -0.0001

Data Index: 364175 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.6928. Min Act: -0.0001

Data Index: 147021 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7125. Min Act: -0.0001

Data Index: 991950 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5771. Min Act: -0.0002

Data Index: 301925 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5616. Min Act: -0.0002

Data Index: 811539 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.6076. Min Act: -0.0002

Data Index: 543282 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5805. Min Act: -0.0001

Data Index: 570753 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5326. Min Act: -0.0002

Data Index: 793112 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.6156. Min Act: -0.0001

Data Index: 181568 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5569. Min Act: -0.0002

Data Index: 1007950 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5729. Min Act: -0.0001

Data Index: 450790 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5063. Min Act: -0.0001

Data Index: 62073 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5362. Min Act: -0.0002

Data Index: 400093 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5743. Min Act: -0.0002

Data Index: 803383 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.4812. Min Act: -0.0001

Data Index: 1143198 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5322. Min Act: -0.0002

Data Index: 637759 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.5259. Min Act: -0.0002

Data Index: 82778 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.4982. Min Act: -0.0002

Data Index: 769227 (C4 (Web Text))

Max Activating Token Index: 793