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

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

Neuron 2317 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2630. Min Range: -2.2630

Max Act: 2.2630. Min Act: -0.0000

Data Index: 335045 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.9816. Min Act: -0.0000

Data Index: 559078 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 2.2630. Min Range: -2.2630

Max Act: 2.0092. Min Act: -0.0000

Data Index: 245981 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 2.2630. Min Range: -2.2630

Max Act: 2.0811. Min Act: -0.0000

Data Index: 1130127 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.8810. Min Act: -0.0000

Data Index: 981820 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.8943. Min Act: -0.0000

Data Index: 1176871 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.8702. Min Act: -0.0000

Data Index: 476340 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.8869. Min Act: -0.0000

Data Index: 542352 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.7251. Min Act: -0.0000

Data Index: 1264055 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.6653. Min Act: -0.0000

Data Index: 637809 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.8510. Min Act: -0.0000

Data Index: 1186399 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.7271. Min Act: -0.0000

Data Index: 715666 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.8310. Min Act: -0.0000

Data Index: 36374 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.4474. Min Act: -0.0000

Data Index: 871635 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.7032. Min Act: -0.0000

Data Index: 491546 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.6938. Min Act: -0.0000

Data Index: 310013 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.7108. Min Act: -0.0000

Data Index: 92026 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.6455. Min Act: -0.0000

Data Index: 1015143 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.5219. Min Act: -0.0000

Data Index: 811858 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 2.2630. Min Range: -2.2630

Max Act: 1.6860. Min Act: -0.0000

Data Index: 992540 (C4 (Web Text))

Max Activating Token Index: 907