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

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

Neuron 3328 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: 0.9102. Min Range: -0.9102

Max Act: 0.9102. Min Act: -0.0002

Data Index: 846496 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.8559. Min Act: -0.0002

Data Index: 65740 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7063. Min Act: -0.0002

Data Index: 508418 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7645. Min Act: -0.0002

Data Index: 109294 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7635. Min Act: -0.0001

Data Index: 1228177 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6818. Min Act: -0.0002

Data Index: 587671 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6772. Min Act: -0.0002

Data Index: 159960 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6522. Min Act: -0.0001

Data Index: 252465 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6918. Min Act: -0.0002

Data Index: 210278 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6714. Min Act: -0.0001

Data Index: 325076 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6738. Min Act: -0.0001

Data Index: 708293 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6518. Min Act: -0.0002

Data Index: 431021 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.7113. Min Act: -0.0001

Data Index: 617038 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6529. Min Act: -0.0001

Data Index: 1210196 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6450. Min Act: -0.0001

Data Index: 691147 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6393. Min Act: -0.0001

Data Index: 1090820 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6542. Min Act: -0.0001

Data Index: 604408 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.6504. Min Act: -0.0002

Data Index: 276702 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.5876. Min Act: -0.0001

Data Index: 506828 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.9102. Min Range: -0.9102

Max Act: 0.5810. Min Act: -0.0002

Data Index: 1072555 (C4 (Web Text))

Max Activating Token Index: 840