Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4221 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.8216. Min Act: -0.0003

Data Index: 1232031 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6888. Min Act: -0.0003

Data Index: 501470 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6961. Min Act: -0.0003

Data Index: 732616 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6141. Min Act: -0.0003

Data Index: 19383 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6035. Min Act: -0.0003

Data Index: 480924 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5753. Min Act: -0.0003

Data Index: 1035648 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5694. Min Act: -0.0003

Data Index: 565837 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5464. Min Act: -0.0003

Data Index: 79135 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5599. Min Act: -0.0003

Data Index: 1201987 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5556. Min Act: -0.0003

Data Index: 826538 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5508. Min Act: -0.0002

Data Index: 590329 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5446. Min Act: -0.0003

Data Index: 475753 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5225. Min Act: -0.0003

Data Index: 1019000 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5380. Min Act: -0.0003

Data Index: 976123 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5521. Min Act: -0.0003

Data Index: 434974 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5393. Min Act: -0.0003

Data Index: 522799 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5261. Min Act: -0.0003

Data Index: 289238 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5013. Min Act: -0.0003

Data Index: 331234 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5151. Min Act: -0.0002

Data Index: 310331 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5129. Min Act: -0.0003

Data Index: 1053484 (C4 (Web Text))

Max Activating Token Index: 563