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

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

Neuron 3157 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2539. Min Act: -0.0000

Data Index: 589021 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2840. Min Act: -0.0001

Data Index: 496199 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2923. Min Act: -0.0001

Data Index: 952051 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2264. Min Act: -0.0000

Data Index: 222925 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2459. Min Act: -0.0000

Data Index: 912065 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2115. Min Act: -0.0000

Data Index: 632157 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2124. Min Act: -0.0001

Data Index: 881922 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1873. Min Act: -0.0001

Data Index: 1189628 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1754. Min Act: -0.0001

Data Index: 164601 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1824. Min Act: -0.0001

Data Index: 89031 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1814. Min Act: -0.0001

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1796. Min Act: -0.0000

Data Index: 373945 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1716. Min Act: -0.0000

Data Index: 155720 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1812. Min Act: -0.0001

Data Index: 554656 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1772. Min Act: -0.0001

Data Index: 116749 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1758. Min Act: -0.0001

Data Index: 113792 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1621. Min Act: -0.0000

Data Index: 480856 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1744. Min Act: -0.0001

Data Index: 117182 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1736. Min Act: -0.0000

Data Index: 610766 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1807. Min Act: -0.0000

Data Index: 377208 (C4 (Web Text))

Max Activating Token Index: 67