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

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

Neuron 1273 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1962. Min Act: -0.0004

Data Index: 970163 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1855. Min Act: -0.0003

Data Index: 673129 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1897. Min Act: -0.0003

Data Index: 1104963 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1806. Min Act: -0.0003

Data Index: 428397 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1841. Min Act: -0.0003

Data Index: 1031828 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1825. Min Act: -0.0003

Data Index: 559948 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1801. Min Act: -0.0003

Data Index: 1228902 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1702. Min Act: -0.0003

Data Index: 1230565 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1712. Min Act: -0.0003

Data Index: 1267475 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1803. Min Act: -0.0003

Data Index: 61781 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1740. Min Act: -0.0003

Data Index: 821076 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1830. Min Act: -0.0003

Data Index: 407579 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1774. Min Act: -0.0003

Data Index: 209674 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1739. Min Act: -0.0003

Data Index: 138488 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1708. Min Act: -0.0003

Data Index: 675659 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1743. Min Act: -0.0003

Data Index: 309159 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1709. Min Act: -0.0003

Data Index: 389088 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1758. Min Act: -0.0003

Data Index: 325678 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1706. Min Act: -0.0003

Data Index: 970569 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.1962. Min Range: -0.1962

Max Act: 0.1704. Min Act: -0.0003

Data Index: 1262794 (C4 (Web Text))

Max Activating Token Index: 456