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

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

Neuron 4054 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.9245. Min Act: -0.0000

Data Index: 510604 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.9230. Min Act: -0.0000

Data Index: 270798 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.8958. Min Act: -0.0000

Data Index: 986629 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.8766. Min Act: 0.0000

Data Index: 426709 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.8580. Min Act: -0.0000

Data Index: 911377 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1325963 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.8121. Min Act: -0.0000

Data Index: 862528 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7740. Min Act: -0.0000

Data Index: 1013910 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7161. Min Act: -0.0000

Data Index: 733900 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1128168 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6816. Min Act: -0.0000

Data Index: 988444 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1247670 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1090555 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6895. Min Act: -0.0000

Data Index: 499616 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7049. Min Act: -0.0000

Data Index: 547130 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6681. Min Act: 0.0001

Data Index: 703707 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6567. Min Act: -0.0000

Data Index: 174897 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6310. Min Act: -0.0000

Data Index: 797125 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6890. Min Act: 0.0000

Data Index: 1341837 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6999. Min Act: -0.0000

Data Index: 363233 (C4 (Web Text))

Max Activating Token Index: 99