Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3367 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.2055. Min Act: -0.0001

Data Index: 446171 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1123788 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0597. Min Act: -0.0000

Data Index: 415174 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1159755 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0606. Min Act: -0.0000

Data Index: 644308 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.9971. Min Act: -0.0000

Data Index: 34462 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1265896 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.9751. Min Act: -0.0000

Data Index: 316675 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.9570. Min Act: -0.0001

Data Index: 664412 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.9166. Min Act: -0.0000

Data Index: 758545 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8585. Min Act: -0.0000

Data Index: 573543 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8745. Min Act: -0.0000

Data Index: 995714 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8713. Min Act: -0.0001

Data Index: 400208 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8397. Min Act: -0.0000

Data Index: 969503 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8177. Min Act: -0.0000

Data Index: 937377 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8068. Min Act: -0.0000

Data Index: 984011 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8258. Min Act: -0.0000

Data Index: 453729 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.7787. Min Act: 0.0001

Data Index: 914917 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1037838 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1159868 (C4 (Web Text))

Max Activating Token Index: 251