Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1251 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0797. Min Act: -0.0001

Data Index: 703446 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0754. Min Act: -0.0001

Data Index: 533531 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1157883 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1352350 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0757. Min Act: -0.0001

Data Index: 55226 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0729. Min Act: -0.0001

Data Index: 250495 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0668. Min Act: -0.0001

Data Index: 282166 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0694. Min Act: -0.0001

Data Index: 894218 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0740. Min Act: -0.0001

Data Index: 165194 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0683. Min Act: -0.0001

Data Index: 455267 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1263519 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0679. Min Act: -0.0001

Data Index: 177249 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0676. Min Act: -0.0001

Data Index: 551225 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1352170 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0697. Min Act: -0.0001

Data Index: 434111 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0671. Min Act: -0.0001

Data Index: 951041 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0664. Min Act: -0.0001

Data Index: 732677 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1124471 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0672. Min Act: -0.0001

Data Index: 271677 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0644. Min Act: -0.0001

Data Index: 426762 (C4 (Web Text))

Max Activating Token Index: 1005