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

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

Neuron 1437 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: 0.0891. Min Range: -0.0891

Max Act: 0.0847. Min Act: -0.0002

Data Index: 900246 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0891. Min Act: -0.0002

Data Index: 259461 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0840. Min Act: -0.0002

Data Index: 771076 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0837. Min Act: -0.0002

Data Index: 725313 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0841. Min Act: -0.0002

Data Index: 291389 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1551150 (Python Code)

Max Activating Token Index: 749

Text #6

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0714. Min Act: -0.0002

Data Index: 191079 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0721. Min Act: -0.0002

Data Index: 18365 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1227679 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0704. Min Act: -0.0002

Data Index: 701087 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1217631 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1152784 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0693. Min Act: -0.0002

Data Index: 802324 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0697. Min Act: -0.0002

Data Index: 951020 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1598789 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1294455 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0695. Min Act: -0.0002

Data Index: 778597 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0667. Min Act: -0.0002

Data Index: 192678 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1150316 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0677. Min Act: -0.0002

Data Index: 297913 (C4 (Web Text))

Max Activating Token Index: 973