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

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

Neuron 1180 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0688. Min Act: -0.0001

Data Index: 396942 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0726. Min Act: -0.0001

Data Index: 633019 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9808. Min Act: -0.0001

Data Index: 481392 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9581. Min Act: -0.0001

Data Index: 802843 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8694. Min Act: -0.0001

Data Index: 618148 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7667. Min Act: -0.0001

Data Index: 143141 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8094. Min Act: -0.0001

Data Index: 1300551 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8552. Min Act: -0.0001

Data Index: 1266010 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7952. Min Act: -0.0001

Data Index: 155911 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7886. Min Act: -0.0001

Data Index: 1295930 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8100. Min Act: -0.0001

Data Index: 734232 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7780. Min Act: -0.0001

Data Index: 452367 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7462. Min Act: -0.0001

Data Index: 737429 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8109. Min Act: -0.0001

Data Index: 677288 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7334. Min Act: -0.0001

Data Index: 640667 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8363. Min Act: -0.0001

Data Index: 1259384 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7410. Min Act: -0.0001

Data Index: 1508497 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7655. Min Act: -0.0001

Data Index: 1239404 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7358. Min Act: -0.0001

Data Index: 968922 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7794. Min Act: -0.0001

Data Index: 1027508 (C4 (Web Text))

Max Activating Token Index: 813