Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2545 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.7880. Min Act: -0.0000

Data Index: 934165 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.8563. Min Act: -0.0000

Data Index: 603163 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.8078. Min Act: -0.0000

Data Index: 1206339 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.6456. Min Act: -0.0000

Data Index: 1171354 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.7031. Min Act: -0.0000

Data Index: 1233732 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.6648. Min Act: 0.0000

Data Index: 1078232 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.7265. Min Act: 0.0000

Data Index: 94812 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.6219. Min Act: -0.0000

Data Index: 58049 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.5539. Min Act: -0.0000

Data Index: 1244310 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.5339. Min Act: 0.0000

Data Index: 389993 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.5229. Min Act: 0.0000

Data Index: 89226 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.5151. Min Act: -0.0000

Data Index: 1055553 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.4759. Min Act: -0.0000

Data Index: 342538 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.4687. Min Act: 0.0000

Data Index: 1093022 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.4543. Min Act: -0.0000

Data Index: 802927 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.4344. Min Act: 0.0001

Data Index: 203605 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.4218. Min Act: -0.0000

Data Index: 465409 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.4207. Min Act: -0.0000

Data Index: 390999 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.3923. Min Act: 0.0001

Data Index: 105033 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.4756. Min Act: -0.0000

Data Index: 981688 (C4 (Web Text))

Max Activating Token Index: 817