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

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

Neuron 2515 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: 0.1029. Min Range: -0.1029

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1026092 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.1026. Min Act: -0.0002

Data Index: 438098 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.1012. Min Act: -0.0002

Data Index: 1199891 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.1010. Min Act: -0.0002

Data Index: 43281 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0935. Min Act: -0.0002

Data Index: 166434 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1027325 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0850. Min Act: -0.0002

Data Index: 354276 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1143549 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1319820 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0715. Min Act: -0.0002

Data Index: 686656 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1135681 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0713. Min Act: -0.0002

Data Index: 820190 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0662. Min Act: -0.0002

Data Index: 919220 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1279234 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0666. Min Act: -0.0002

Data Index: 507680 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0687. Min Act: -0.0002

Data Index: 24371 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1091526 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0660. Min Act: -0.0002

Data Index: 902955 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0689. Min Act: -0.0002

Data Index: 584510 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0660. Min Act: -0.0002

Data Index: 443896 (C4 (Web Text))

Max Activating Token Index: 632