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

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

Neuron 4706 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: 0.3837. Min Range: -0.3837

Max Act: 0.3837. Min Act: -0.0000

Data Index: 299765 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1340938 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1039230 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3739. Min Act: -0.0000

Data Index: 889114 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1094513 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3556. Min Act: -0.0000

Data Index: 603502 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1011081 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3399. Min Act: -0.0000

Data Index: 28662 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1214630 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3463. Min Act: -0.0000

Data Index: 223245 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1300640 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1049729 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1094773 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3018. Min Act: -0.0000

Data Index: 752994 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3198. Min Act: -0.0000

Data Index: 503724 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3167. Min Act: -0.0000

Data Index: 909997 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1086596 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1096970 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2888. Min Act: -0.0000

Data Index: 116655 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2966. Min Act: -0.0000

Data Index: 883250 (C4 (Web Text))

Max Activating Token Index: 586