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

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

Neuron 1635 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2262. Min Act: -0.0001

Data Index: 20662 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2292. Min Act: -0.0001

Data Index: 379810 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2182. Min Act: -0.0001

Data Index: 822067 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2002. Min Act: -0.0001

Data Index: 113780 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2007. Min Act: -0.0001

Data Index: 765913 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2367. Min Act: -0.0001

Data Index: 109907 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2026. Min Act: -0.0001

Data Index: 162580 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1089374 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1953. Min Act: -0.0001

Data Index: 888457 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1938. Min Act: -0.0001

Data Index: 426516 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1823. Min Act: -0.0001

Data Index: 439124 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1870. Min Act: -0.0001

Data Index: 24843 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1905. Min Act: -0.0001

Data Index: 616961 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1771. Min Act: -0.0001

Data Index: 523892 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1813. Min Act: -0.0001

Data Index: 485509 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1135770 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1854. Min Act: -0.0001

Data Index: 329065 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1300262 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1750. Min Act: -0.0001

Data Index: 1310721 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.1734. Min Act: -0.0001

Data Index: 56757 (C4 (Web Text))

Max Activating Token Index: 170