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

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

Neuron 1842 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7613. Min Act: -0.0000

Data Index: 1094745 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.8598. Min Act: -0.0000

Data Index: 261642 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7264. Min Act: -0.0000

Data Index: 403553 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.8158. Min Act: -0.0000

Data Index: 935350 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.8018. Min Act: -0.0000

Data Index: 142659 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7065. Min Act: -0.0000

Data Index: 829381 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.6981. Min Act: -0.0000

Data Index: 547531 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7019. Min Act: -0.0000

Data Index: 167354 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.8007. Min Act: -0.0000

Data Index: 357365 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.8778. Min Act: -0.0000

Data Index: 595129 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.5987. Min Act: -0.0000

Data Index: 1332990 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7766. Min Act: -0.0000

Data Index: 510926 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7863. Min Act: -0.0000

Data Index: 908021 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.9011. Min Act: -0.0000

Data Index: 1069123 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7652. Min Act: -0.0000

Data Index: 763959 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7669. Min Act: -0.0000

Data Index: 372848 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7492. Min Act: -0.0000

Data Index: 844439 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.6724. Min Act: -0.0000

Data Index: 1133682 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.6630. Min Act: -0.0000

Data Index: 1200075 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 1.9011. Min Range: -1.9011

Max Act: 1.7443. Min Act: -0.0000

Data Index: 313345 (C4 (Web Text))

Max Activating Token Index: 44