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

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

Neuron 1705 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1002211 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3538. Min Act: -0.0000

Data Index: 90223 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3369. Min Act: -0.0000

Data Index: 408166 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2965. Min Act: -0.0000

Data Index: 923596 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3482. Min Act: -0.0000

Data Index: 438576 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3211. Min Act: -0.0000

Data Index: 843601 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1644751 (Python Code)

Max Activating Token Index: 750

Text #7

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1637382 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3055. Min Act: -0.0000

Data Index: 179365 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3046. Min Act: -0.0000

Data Index: 841681 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1579115 (Python Code)

Max Activating Token Index: 262

Text #11

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2994. Min Act: -0.0000

Data Index: 355923 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1240195 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2931. Min Act: -0.0000

Data Index: 387979 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2709. Min Act: -0.0000

Data Index: 91695 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2966. Min Act: -0.0000

Data Index: 136343 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1642281 (Python Code)

Max Activating Token Index: 984

Text #17

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2918. Min Act: -0.0000

Data Index: 475803 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2705. Min Act: -0.0000

Data Index: 431459 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1036521 (C4 (Web Text))

Max Activating Token Index: 724