Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1596 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4495. Min Act: -0.0001

Data Index: 1092113 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3137. Min Act: -0.0001

Data Index: 333970 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3151. Min Act: -0.0001

Data Index: 665357 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1331535 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2918. Min Act: -0.0001

Data Index: 176636 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3180. Min Act: -0.0001

Data Index: 594643 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2752. Min Act: -0.0001

Data Index: 1121382 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2720. Min Act: -0.0001

Data Index: 294841 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2925. Min Act: -0.0001

Data Index: 732171 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2718. Min Act: -0.0001

Data Index: 469444 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1114776 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2876. Min Act: -0.0001

Data Index: 566630 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2776. Min Act: -0.0001

Data Index: 1094935 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2864. Min Act: -0.0001

Data Index: 1347757 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2657. Min Act: -0.0001

Data Index: 808952 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2757. Min Act: -0.0001

Data Index: 257143 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2744. Min Act: -0.0001

Data Index: 225067 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2714. Min Act: -0.0001

Data Index: 496915 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2727. Min Act: -0.0001

Data Index: 226062 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2839. Min Act: -0.0001

Data Index: 1120917 (C4 (Web Text))

Max Activating Token Index: 354