Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 602 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0783. Min Act: -0.0002

Data Index: 32936 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0771. Min Act: -0.0002

Data Index: 868825 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0745. Min Act: -0.0002

Data Index: 473249 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0737. Min Act: -0.0002

Data Index: 949189 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0797. Min Act: -0.0002

Data Index: 630794 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0764. Min Act: -0.0002

Data Index: 312687 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0681. Min Act: -0.0002

Data Index: 985498 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0758. Min Act: -0.0002

Data Index: 235954 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0718. Min Act: -0.0002

Data Index: 589448 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0697. Min Act: -0.0002

Data Index: 779077 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0735. Min Act: -0.0002

Data Index: 42488 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0707. Min Act: -0.0002

Data Index: 796969 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0681. Min Act: -0.0002

Data Index: 120429 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0680. Min Act: -0.0002

Data Index: 489427 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0707. Min Act: -0.0002

Data Index: 201594 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0738. Min Act: -0.0002

Data Index: 616305 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0666. Min Act: -0.0002

Data Index: 186417 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0688. Min Act: -0.0002

Data Index: 137470 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0680. Min Act: -0.0002

Data Index: 27282 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0683. Min Act: -0.0002

Data Index: 602510 (C4 (Web Text))

Max Activating Token Index: 985