Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2995 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0002

Data Index: 104719 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1644212 (Python Code)

Max Activating Token Index: 651

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0711. Min Act: -0.0001

Data Index: 127734 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0671. Min Act: -0.0001

Data Index: 683125 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1553714 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0689. Min Act: -0.0002

Data Index: 561155 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0678. Min Act: -0.0002

Data Index: 627923 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0670. Min Act: -0.0001

Data Index: 236848 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1377243 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0643. Min Act: -0.0002

Data Index: 293074 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1607716 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1597550 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1354922 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1497257 (Python Code)

Max Activating Token Index: 749

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0634. Min Act: -0.0002

Data Index: 812560 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1117154 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0674. Min Act: -0.0002

Data Index: 828174 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0649. Min Act: -0.0001

Data Index: 265903 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1562658 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1121811 (C4 (Web Text))

Max Activating Token Index: 1004