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

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

Neuron 120 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5074. Min Range: -2.5074

Max Act: 2.5074. Min Act: -0.0000

Data Index: 800138 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 2.5074. Min Range: -2.5074

Max Act: 2.2241. Min Act: -0.0000

Data Index: 112020 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 2.5074. Min Range: -2.5074

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1302667 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 2.5074. Min Range: -2.5074

Max Act: 2.2421. Min Act: -0.0000

Data Index: 737860 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 2.5074. Min Range: -2.5074

Max Act: 2.0103. Min Act: -0.0000

Data Index: 1240682 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 2.5074. Min Range: -2.5074

Max Act: 2.0215. Min Act: -0.0000

Data Index: 830855 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.9824. Min Act: -0.0000

Data Index: 355885 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.9566. Min Act: -0.0000

Data Index: 968323 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.9579. Min Act: -0.0000

Data Index: 837393 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.9340. Min Act: -0.0000

Data Index: 855343 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.8350. Min Act: -0.0000

Data Index: 510128 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 2.5074. Min Range: -2.5074

Max Act: 2.0378. Min Act: -0.0000

Data Index: 478500 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.8993. Min Act: -0.0000

Data Index: 719205 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 2.5074. Min Range: -2.5074

Max Act: 2.0001. Min Act: -0.0000

Data Index: 349511 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.6853. Min Act: -0.0000

Data Index: 229857 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.9950. Min Act: -0.0000

Data Index: 332470 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.7959. Min Act: -0.0000

Data Index: 106876 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.8564. Min Act: -0.0000

Data Index: 104059 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.9515. Min Act: -0.0000

Data Index: 740138 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 2.5074. Min Range: -2.5074

Max Act: 1.8745. Min Act: -0.0000

Data Index: 154983 (C4 (Web Text))

Max Activating Token Index: 219