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

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

Neuron 2026 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.4017. Min Act: -0.0000

Data Index: 173327 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.3194. Min Act: -0.0000

Data Index: 515611 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1199789 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.2413. Min Act: -0.0000

Data Index: 500133 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.2147. Min Act: -0.0000

Data Index: 1053837 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1002652 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.1305. Min Act: -0.0000

Data Index: 773319 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1181316 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.1203. Min Act: -0.0000

Data Index: 1121423 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.1061. Min Act: -0.0000

Data Index: 759609 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.1080. Min Act: -0.0000

Data Index: 1334904 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.0907. Min Act: -0.0000

Data Index: 355440 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1275425 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.1590. Min Act: -0.0000

Data Index: 864995 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.0630. Min Act: -0.0000

Data Index: 1224185 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1197543 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1100741 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.1091. Min Act: -0.0000

Data Index: 1328065 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.9750. Min Act: -0.0000

Data Index: 45115 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1035048 (C4 (Web Text))

Max Activating Token Index: 788