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

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

Neuron 5072 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.9157. Min Act: -0.0000

Data Index: 438697 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.8284. Min Act: -0.0000

Data Index: 727145 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.7875. Min Act: -0.0000

Data Index: 415762 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.7416. Min Act: -0.0000

Data Index: 96702 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.7110. Min Act: -0.0000

Data Index: 576693 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.6844. Min Act: -0.0000

Data Index: 972409 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.6793. Min Act: -0.0000

Data Index: 371794 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.7259. Min Act: -0.0000

Data Index: 431601 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.5266. Min Act: -0.0000

Data Index: 231171 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1096486 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.5854. Min Act: -0.0000

Data Index: 1289568 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.6683. Min Act: -0.0000

Data Index: 990106 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.6553. Min Act: -0.0000

Data Index: 71000 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.6623. Min Act: -0.0000

Data Index: 1332408 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.5674. Min Act: -0.0000

Data Index: 1022166 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.5608. Min Act: -0.0000

Data Index: 56615 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.5608. Min Act: -0.0000

Data Index: 155013 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.5262. Min Act: -0.0000

Data Index: 351836 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.5369. Min Act: -0.0000

Data Index: 887071 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 1.9157. Min Range: -1.9157

Max Act: 1.5144. Min Act: -0.0000

Data Index: 1147364 (C4 (Web Text))

Max Activating Token Index: 597