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

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

Neuron 3734 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: 1.8381. Min Range: -1.8381

Max Act: 1.8381. Min Act: -0.0002

Data Index: 726055 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.7390. Min Act: -0.0002

Data Index: 567261 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.5755. Min Act: -0.0002

Data Index: 1049805 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.4614. Min Act: -0.0002

Data Index: 1060074 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.5244. Min Act: -0.0002

Data Index: 6012 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.6453. Min Act: -0.0002

Data Index: 896849 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.4766. Min Act: -0.0002

Data Index: 534110 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.5506. Min Act: -0.0002

Data Index: 880833 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.7978. Min Act: -0.0002

Data Index: 463301 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.4556. Min Act: -0.0002

Data Index: 427102 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.4817. Min Act: -0.0002

Data Index: 1177112 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.5689. Min Act: -0.0002

Data Index: 330018 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.4411. Min Act: -0.0002

Data Index: 179953 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.5190. Min Act: -0.0002

Data Index: 1333537 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.5080. Min Act: -0.0002

Data Index: 1212618 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.6256. Min Act: -0.0002

Data Index: 1344770 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.6775. Min Act: -0.0002

Data Index: 769560 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3057. Min Act: -0.0002

Data Index: 835501 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.5217. Min Act: -0.0002

Data Index: 921603 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3598. Min Act: -0.0002

Data Index: 400144 (C4 (Web Text))

Max Activating Token Index: 953