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

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

Neuron 4620 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1650. Min Range: -1.1650

Max Act: 1.1650. Min Act: -0.0000

Data Index: 993873 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1073115 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.7765. Min Act: -0.0000

Data Index: 773014 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.6331. Min Act: -0.0000

Data Index: 984687 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.6570. Min Act: -0.0000

Data Index: 985389 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1131706 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.7079. Min Act: -0.0000

Data Index: 286426 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.6930. Min Act: -0.0000

Data Index: 967544 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1080942 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1004748 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.5442. Min Act: -0.0000

Data Index: 576183 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.5824. Min Act: -0.0000

Data Index: 604435 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.5317. Min Act: -0.0000

Data Index: 676871 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1247806 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.5010. Min Act: -0.0000

Data Index: 79342 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1291758 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1019605 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1137077 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.5244. Min Act: -0.0000

Data Index: 126538 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.4710. Min Act: -0.0000

Data Index: 370018 (C4 (Web Text))

Max Activating Token Index: 766