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

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

Neuron 149 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.4157. Min Act: -0.0000

Data Index: 991419 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3540. Min Act: -0.0000

Data Index: 310498 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3341. Min Act: -0.0000

Data Index: 216981 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3304. Min Act: -0.0000

Data Index: 994650 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3245. Min Act: -0.0000

Data Index: 850869 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3412. Min Act: -0.0000

Data Index: 50396 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1150389 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1137939 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2659. Min Act: -0.0000

Data Index: 298674 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2940. Min Act: -0.0000

Data Index: 315827 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2854. Min Act: -0.0000

Data Index: 443970 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1153510 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2811. Min Act: -0.0000

Data Index: 264593 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2754. Min Act: -0.0000

Data Index: 258459 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2707. Min Act: -0.0000

Data Index: 81999 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2613. Min Act: -0.0000

Data Index: 739834 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2701. Min Act: -0.0000

Data Index: 886996 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2645. Min Act: -0.0000

Data Index: 125078 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2717. Min Act: -0.0000

Data Index: 299018 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1322888 (C4 (Web Text))

Max Activating Token Index: 955