Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 959 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0994. Min Act: -0.0002

Data Index: 619712 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0746. Min Act: -0.0002

Data Index: 998814 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0789. Min Act: -0.0002

Data Index: 492680 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0771. Min Act: -0.0002

Data Index: 983778 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1301378 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0761. Min Act: -0.0002

Data Index: 68511 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0727. Min Act: -0.0002

Data Index: 402759 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0726. Min Act: -0.0002

Data Index: 565734 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0743. Min Act: -0.0001

Data Index: 106191 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0681. Min Act: -0.0002

Data Index: 466603 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1273150 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0698. Min Act: -0.0002

Data Index: 569600 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0680. Min Act: -0.0002

Data Index: 510505 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0701. Min Act: -0.0002

Data Index: 779988 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1192619 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0693. Min Act: -0.0002

Data Index: 417497 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0675. Min Act: -0.0002

Data Index: 289848 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0701. Min Act: -0.0002

Data Index: 949995 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0666. Min Act: -0.0002

Data Index: 56535 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1329152 (C4 (Web Text))

Max Activating Token Index: 563