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

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

Neuron 4734 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.7633. Min Act: -0.0000

Data Index: 567964 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.6009. Min Act: -0.0000

Data Index: 145748 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.3978. Min Act: -0.0000

Data Index: 1307983 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.4726. Min Act: -0.0000

Data Index: 797225 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.4123. Min Act: -0.0000

Data Index: 126470 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.2850. Min Act: -0.0000

Data Index: 269653 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.2501. Min Act: -0.0000

Data Index: 920245 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1307151 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.3726. Min Act: -0.0000

Data Index: 273489 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.3570. Min Act: -0.0000

Data Index: 654503 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.2724. Min Act: -0.0000

Data Index: 468220 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.2759. Min Act: -0.0000

Data Index: 1147137 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1200641 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.1983. Min Act: -0.0000

Data Index: 903205 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.1818. Min Act: -0.0000

Data Index: 293473 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.2614. Min Act: -0.0000

Data Index: 651870 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.2539. Min Act: -0.0000

Data Index: 551963 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.1723. Min Act: -0.0000

Data Index: 614702 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.2470. Min Act: -0.0000

Data Index: 765822 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 1.7633. Min Range: -1.7633

Max Act: 1.2307. Min Act: -0.0000

Data Index: 738967 (C4 (Web Text))

Max Activating Token Index: 1001