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

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

Neuron 3597 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.5029. Min Act: -0.0000

Data Index: 482129 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4697. Min Act: -0.0000

Data Index: 265580 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4433. Min Act: -0.0001

Data Index: 558015 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4649. Min Act: -0.0000

Data Index: 920045 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4292. Min Act: -0.0000

Data Index: 479220 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4093. Min Act: -0.0000

Data Index: 738661 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4327. Min Act: -0.0001

Data Index: 91924 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3844. Min Act: -0.0000

Data Index: 671430 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3857. Min Act: -0.0000

Data Index: 292801 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3972. Min Act: -0.0001

Data Index: 988974 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4055. Min Act: -0.0000

Data Index: 716497 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3190. Min Act: -0.0000

Data Index: 718470 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3920. Min Act: -0.0000

Data Index: 803828 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3984. Min Act: -0.0000

Data Index: 766008 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3695. Min Act: -0.0000

Data Index: 372548 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3670. Min Act: -0.0000

Data Index: 104570 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3687. Min Act: -0.0001

Data Index: 1262077 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3817. Min Act: -0.0000

Data Index: 702269 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1315796 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.3254. Min Act: -0.0001

Data Index: 356405 (C4 (Web Text))

Max Activating Token Index: 126