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

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

Neuron 4159 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8804. Min Range: -4.8804

Max Act: 4.8804. Min Act: -0.0000

Data Index: 108866 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 4.8804. Min Range: -4.8804

Max Act: 4.6536. Min Act: -0.0000

Data Index: 769244 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 4.8804. Min Range: -4.8804

Max Act: 4.1708. Min Act: -0.0000

Data Index: 1086010 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 4.8804. Min Range: -4.8804

Max Act: 4.2936. Min Act: -0.0000

Data Index: 548678 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.9018. Min Act: -0.0000

Data Index: 1122880 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 4.8804. Min Range: -4.8804

Max Act: 4.3659. Min Act: -0.0000

Data Index: 1044190 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 4.8804. Min Range: -4.8804

Max Act: 4.3329. Min Act: -0.0000

Data Index: 121703 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 4.8804. Min Range: -4.8804

Max Act: 4.0041. Min Act: -0.0000

Data Index: 1052509 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 4.8804. Min Range: -4.8804

Max Act: 4.2041. Min Act: -0.0000

Data Index: 810636 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.8662. Min Act: -0.0000

Data Index: 853406 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.8247. Min Act: -0.0000

Data Index: 1056865 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.8261. Min Act: -0.0000

Data Index: 531170 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.6449. Min Act: -0.0000

Data Index: 697334 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.7772. Min Act: -0.0000

Data Index: 416814 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.6211. Min Act: -0.0000

Data Index: 123542 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.7235. Min Act: -0.0000

Data Index: 662656 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.8277. Min Act: -0.0000

Data Index: 172046 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.5017. Min Act: -0.0000

Data Index: 440644 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.6572. Min Act: -0.0000

Data Index: 1338943 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 4.8804. Min Range: -4.8804

Max Act: 3.6251. Min Act: -0.0000

Data Index: 640225 (C4 (Web Text))

Max Activating Token Index: 427