Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2686 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1304. Min Act: -0.0000

Data Index: 220894 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1127. Min Act: -0.0000

Data Index: 783928 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1052. Min Act: -0.0000

Data Index: 420130 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1056. Min Act: -0.0000

Data Index: 410854 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1235672 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0908. Min Act: -0.0000

Data Index: 348661 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0859. Min Act: -0.0000

Data Index: 884427 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0863. Min Act: -0.0000

Data Index: 368823 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1267040 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0923. Min Act: -0.0000

Data Index: 597008 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0878. Min Act: -0.0000

Data Index: 795217 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1312730 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0837. Min Act: -0.0000

Data Index: 65964 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0790. Min Act: -0.0000

Data Index: 312758 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0776. Min Act: -0.0000

Data Index: 284286 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0757. Min Act: -0.0000

Data Index: 497766 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1091205 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0780. Min Act: -0.0000

Data Index: 750013 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0782. Min Act: -0.0000

Data Index: 854664 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1266599 (C4 (Web Text))

Max Activating Token Index: 17