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

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

Neuron 720 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0801. Min Act: -0.0006

Data Index: 167720 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0787. Min Act: -0.0006

Data Index: 144131 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0791. Min Act: -0.0006

Data Index: 535795 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: -0.0006

Data Index: 788893 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0734. Min Act: -0.0006

Data Index: 1004521 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0747. Min Act: -0.0006

Data Index: 860983 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0773. Min Act: -0.0006

Data Index: 310933 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0768. Min Act: -0.0006

Data Index: 1023770 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0723. Min Act: -0.0006

Data Index: 737342 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0795. Min Act: -0.0006

Data Index: 1352382 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0758. Min Act: -0.0006

Data Index: 159090 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0727. Min Act: -0.0006

Data Index: 1310714 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0798. Min Act: -0.0006

Data Index: 956427 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0766. Min Act: -0.0006

Data Index: 694030 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0732. Min Act: -0.0006

Data Index: 519860 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0788. Min Act: -0.0006

Data Index: 1280334 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0785. Min Act: -0.0006

Data Index: 846454 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0800. Min Act: -0.0006

Data Index: 974210 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0735. Min Act: -0.0006

Data Index: 1188061 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0722. Min Act: -0.0006

Data Index: 129977 (C4 (Web Text))

Max Activating Token Index: 655