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

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

Neuron 4536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0321. Min Range: -6.0321

Max Act: 6.0321. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 6.0321. Min Range: -6.0321

Max Act: 5.7335. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 6.0321. Min Range: -6.0321

Max Act: 5.5213. Min Act: -0.0000

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.9502. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.8013. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.6981. Min Act: -0.0001

Data Index: 591205 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 6.0321. Min Range: -6.0321

Max Act: 5.2232. Min Act: -0.0000

Data Index: 843315 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.6842. Min Act: -0.0001

Data Index: 143353 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.1945. Min Act: -0.0001

Data Index: 121232 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.0100. Min Act: -0.0000

Data Index: 187969 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.2689. Min Act: -0.0000

Data Index: 200100 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.0119. Min Act: -0.0001

Data Index: 213197 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 6.0321. Min Range: -6.0321

Max Act: 3.7178. Min Act: -0.0000

Data Index: 630024 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.1546. Min Act: -0.0001

Data Index: 1054314 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.2807. Min Act: -0.0001

Data Index: 877669 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.1470. Min Act: -0.0001

Data Index: 1008201 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 6.0321. Min Range: -6.0321

Max Act: 3.9785. Min Act: -0.0001

Data Index: 139890 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 6.0321. Min Range: -6.0321

Max Act: 4.4247. Min Act: -0.0001

Data Index: 428264 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 6.0321. Min Range: -6.0321

Max Act: 3.7328. Min Act: -0.0001

Data Index: 903388 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 6.0321. Min Range: -6.0321

Max Act: 3.6508. Min Act: -0.0001

Data Index: 856708 (C4 (Web Text))

Max Activating Token Index: 197