Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 624 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.2047. Min Act: -0.0002

Data Index: 221130 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.1331. Min Act: -0.0002

Data Index: 1151910 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0974. Min Act: -0.0002

Data Index: 1079530 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0654. Min Act: -0.0002

Data Index: 987107 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0544. Min Act: -0.0002

Data Index: 1298464 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0398. Min Act: -0.0002

Data Index: 998224 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8845. Min Act: -0.0002

Data Index: 190474 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0631. Min Act: -0.0002

Data Index: 908246 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0304. Min Act: -0.0002

Data Index: 869873 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9974. Min Act: -0.0002

Data Index: 330515 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9566. Min Act: -0.0002

Data Index: 789619 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9809. Min Act: -0.0002

Data Index: 1339661 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8809. Min Act: -0.0002

Data Index: 1060212 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9908. Min Act: -0.0002

Data Index: 128019 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0504. Min Act: -0.0002

Data Index: 1121197 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9578. Min Act: -0.0002

Data Index: 12921 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0181. Min Act: -0.0002

Data Index: 816907 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9255. Min Act: -0.0002

Data Index: 423866 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9099. Min Act: -0.0002

Data Index: 861001 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9364. Min Act: -0.0002

Data Index: 61687 (C4 (Web Text))

Max Activating Token Index: 11