Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3665 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.3692. Min Act: -0.0000

Data Index: 632045 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.9391. Min Act: -0.0000

Data Index: 836280 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 6.3692. Min Range: -6.3692

Max Act: 6.1188. Min Act: -0.0000

Data Index: 381102 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.8987. Min Act: -0.0000

Data Index: 1300768 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.8375. Min Act: -0.0000

Data Index: 711776 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.4206. Min Act: -0.0000

Data Index: 1236104 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.3053. Min Act: -0.0000

Data Index: 169182 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.6733. Min Act: -0.0000

Data Index: 806677 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.4748. Min Act: -0.0000

Data Index: 195770 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.1997. Min Act: -0.0000

Data Index: 202315 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.3685. Min Act: -0.0000

Data Index: 485519 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.1669. Min Act: -0.0000

Data Index: 352920 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.3016. Min Act: -0.0000

Data Index: 247515 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.1126. Min Act: -0.0000

Data Index: 261869 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.1842. Min Act: -0.0000

Data Index: 1143701 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 6.3692. Min Range: -6.3692

Max Act: 4.8283. Min Act: -0.0000

Data Index: 1275145 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.1555. Min Act: -0.0000

Data Index: 118920 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 6.3692. Min Range: -6.3692

Max Act: 4.9115. Min Act: -0.0000

Data Index: 600479 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.0924. Min Act: -0.0000

Data Index: 914189 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 6.3692. Min Range: -6.3692

Max Act: 5.0317. Min Act: -0.0000

Data Index: 788571 (C4 (Web Text))

Max Activating Token Index: 953