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

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

Neuron 2806 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: 0.4804. Min Range: -0.4804

Max Act: 0.4503. Min Act: -0.0000

Data Index: 787453 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4636. Min Act: -0.0000

Data Index: 870649 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4804. Min Act: -0.0000

Data Index: 499348 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4550. Min Act: -0.0000

Data Index: 142570 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1142805 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4740. Min Act: -0.0000

Data Index: 390999 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4376. Min Act: -0.0000

Data Index: 977956 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1034062 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1318532 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4051. Min Act: -0.0000

Data Index: 94021 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.3910. Min Act: -0.0000

Data Index: 264478 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4282. Min Act: -0.0000

Data Index: 140743 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1099606 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4066. Min Act: -0.0000

Data Index: 4450 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4083. Min Act: -0.0000

Data Index: 735490 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.3902. Min Act: -0.0000

Data Index: 337780 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1043606 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.3937. Min Act: -0.0000

Data Index: 468830 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.3801. Min Act: -0.0000

Data Index: 204049 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.4804. Min Range: -0.4804

Max Act: 0.3949. Min Act: -0.0000

Data Index: 395509 (C4 (Web Text))

Max Activating Token Index: 841