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

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

Neuron 861 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8651. Min Act: -0.0002

Data Index: 713820 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.9035. Min Act: -0.0001

Data Index: 1112109 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8141. Min Act: -0.0001

Data Index: 1109043 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8551. Min Act: -0.0001

Data Index: 426199 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7982. Min Act: -0.0002

Data Index: 1064385 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7654. Min Act: -0.0001

Data Index: 77395 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7590. Min Act: -0.0002

Data Index: 904083 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8135. Min Act: -0.0002

Data Index: 1325617 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8385. Min Act: -0.0002

Data Index: 1051874 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6949. Min Act: -0.0001

Data Index: 46717 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7327. Min Act: -0.0002

Data Index: 1323981 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7860. Min Act: -0.0001

Data Index: 1271747 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7607. Min Act: -0.0002

Data Index: 1240462 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7647. Min Act: -0.0001

Data Index: 1038807 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7360. Min Act: -0.0001

Data Index: 777478 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7646. Min Act: -0.0001

Data Index: 1034190 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7805. Min Act: -0.0002

Data Index: 1090497 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8292. Min Act: -0.0001

Data Index: 923526 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7469. Min Act: -0.0002

Data Index: 149558 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7277. Min Act: -0.0001

Data Index: 745761 (C4 (Web Text))

Max Activating Token Index: 460