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

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

Neuron 3155 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9811. Min Act: -0.0002

Data Index: 535601 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9002. Min Act: -0.0002

Data Index: 349372 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8582. Min Act: -0.0002

Data Index: 576001 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8573. Min Act: -0.0002

Data Index: 1340881 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8800. Min Act: -0.0002

Data Index: 1148660 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8043. Min Act: -0.0002

Data Index: 1247597 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8380. Min Act: -0.0002

Data Index: 584141 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8561. Min Act: -0.0002

Data Index: 963550 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7945. Min Act: -0.0002

Data Index: 1079877 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7883. Min Act: -0.0002

Data Index: 827950 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7894. Min Act: -0.0002

Data Index: 1003459 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7246. Min Act: -0.0002

Data Index: 1306145 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.6961. Min Act: -0.0002

Data Index: 945269 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7389. Min Act: -0.0002

Data Index: 241922 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7081. Min Act: -0.0002

Data Index: 584282 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7307. Min Act: -0.0002

Data Index: 1186201 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7302. Min Act: -0.0002

Data Index: 656974 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7282. Min Act: -0.0002

Data Index: 30441 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7290. Min Act: -0.0002

Data Index: 526763 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7124. Min Act: -0.0002

Data Index: 134138 (C4 (Web Text))

Max Activating Token Index: 810