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

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

Neuron 335 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: 0.0835. Min Range: -0.0835

Max Act: 0.0835. Min Act: -0.0002

Data Index: 537593 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0815. Min Act: -0.0002

Data Index: 926654 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1008220 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1141792 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1015066 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0803. Min Act: -0.0002

Data Index: 359717 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1309471 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0787. Min Act: -0.0002

Data Index: 738252 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0772. Min Act: -0.0002

Data Index: 751448 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1185669 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0757. Min Act: -0.0002

Data Index: 699666 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0714. Min Act: -0.0002

Data Index: 565142 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0762. Min Act: -0.0002

Data Index: 837076 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1345245 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0735. Min Act: -0.0002

Data Index: 762547 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0759. Min Act: -0.0002

Data Index: 50385 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0721. Min Act: -0.0002

Data Index: 842924 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1304443 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0731. Min Act: -0.0002

Data Index: 571756 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0729. Min Act: -0.0002

Data Index: 533307 (C4 (Web Text))

Max Activating Token Index: 88