Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1561 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.3089. Min Act: -0.0002

Data Index: 1078615 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.3124. Min Act: -0.0002

Data Index: 569674 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2910. Min Act: -0.0002

Data Index: 728628 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2961. Min Act: -0.0002

Data Index: 861172 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2946. Min Act: -0.0002

Data Index: 1174006 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2967. Min Act: -0.0002

Data Index: 102244 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2839. Min Act: -0.0002

Data Index: 1248708 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2955. Min Act: -0.0002

Data Index: 1029806 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2812. Min Act: -0.0002

Data Index: 1229663 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2459. Min Act: -0.0002

Data Index: 727574 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2713. Min Act: -0.0002

Data Index: 303282 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2737. Min Act: -0.0002

Data Index: 1124150 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2564. Min Act: -0.0002

Data Index: 868547 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2667. Min Act: -0.0002

Data Index: 392795 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2436. Min Act: -0.0002

Data Index: 424824 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2624. Min Act: -0.0002

Data Index: 254057 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2242. Min Act: -0.0002

Data Index: 192698 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2338. Min Act: -0.0002

Data Index: 1234363 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2454. Min Act: -0.0002

Data Index: 183241 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2798. Min Act: -0.0002

Data Index: 1039788 (C4 (Web Text))

Max Activating Token Index: 988