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

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

Neuron 3673 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3704. Min Act: -0.0003

Data Index: 603459 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3209. Min Act: -0.0003

Data Index: 369296 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3078. Min Act: -0.0003

Data Index: 1326387 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3044. Min Act: -0.0003

Data Index: 1228326 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2874. Min Act: -0.0003

Data Index: 291012 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2869. Min Act: -0.0003

Data Index: 1344744 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2858. Min Act: -0.0003

Data Index: 357800 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2839. Min Act: -0.0003

Data Index: 1082051 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2766. Min Act: -0.0003

Data Index: 1012297 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2739. Min Act: -0.0003

Data Index: 703437 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2730. Min Act: -0.0003

Data Index: 836858 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2728. Min Act: -0.0003

Data Index: 533778 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2715. Min Act: -0.0003

Data Index: 1071757 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2709. Min Act: -0.0003

Data Index: 1046567 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2516. Min Act: -0.0003

Data Index: 1268455 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2898. Min Act: -0.0003

Data Index: 466335 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2699. Min Act: -0.0003

Data Index: 1178875 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2697. Min Act: -0.0003

Data Index: 324332 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2692. Min Act: -0.0003

Data Index: 744516 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2685. Min Act: -0.0003

Data Index: 534984 (C4 (Web Text))

Max Activating Token Index: 968