Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 444 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1152. Min Act: -0.0003

Data Index: 999068 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0705. Min Act: -0.0003

Data Index: 561238 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0875. Min Act: -0.0003

Data Index: 145617 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0716. Min Act: -0.0003

Data Index: 197676 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0837. Min Act: -0.0003

Data Index: 1198077 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0871. Min Act: -0.0003

Data Index: 1157460 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1588749 (Python Code)

Max Activating Token Index: 1002

Text #7

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0731. Min Act: -0.0003

Data Index: 315799 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1543722 (Python Code)

Max Activating Token Index: 269

Text #9

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1299251 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0781. Min Act: -0.0002

Data Index: 88517 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1429871 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1626525 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0814. Min Act: -0.0003

Data Index: 861896 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1461987 (Python Code)

Max Activating Token Index: 120

Text #15

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1583115 (Python Code)

Max Activating Token Index: 456

Text #16

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1523774 (Python Code)

Max Activating Token Index: 763

Text #17

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0697. Min Act: -0.0004

Data Index: 475138 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1128877 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1449437 (Python Code)

Max Activating Token Index: 293