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

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

Neuron 3990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0079. Min Range: -2.0079

Max Act: 2.0079. Min Act: -0.0000

Data Index: 397887 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.9571. Min Act: -0.0000

Data Index: 1335947 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.9042. Min Act: -0.0000

Data Index: 133934 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.8539. Min Act: -0.0000

Data Index: 242696 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.7684. Min Act: -0.0000

Data Index: 1115212 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.7759. Min Act: -0.0000

Data Index: 779973 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.7254. Min Act: -0.0000

Data Index: 1093455 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.6800. Min Act: -0.0000

Data Index: 18427 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.5986. Min Act: -0.0000

Data Index: 663754 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.7268. Min Act: -0.0000

Data Index: 156898 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.5855. Min Act: -0.0000

Data Index: 149745 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.5812. Min Act: -0.0000

Data Index: 326878 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.5842. Min Act: -0.0000

Data Index: 270512 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.6312. Min Act: -0.0000

Data Index: 1119008 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.7028. Min Act: -0.0000

Data Index: 77492 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.5090. Min Act: -0.0000

Data Index: 736476 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.4008. Min Act: -0.0000

Data Index: 1029114 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.4749. Min Act: -0.0000

Data Index: 938662 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.4944. Min Act: -0.0000

Data Index: 369101 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 2.0079. Min Range: -2.0079

Max Act: 1.6155. Min Act: -0.0000

Data Index: 1217533 (C4 (Web Text))

Max Activating Token Index: 702