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

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

Neuron 533 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0426. Min Act: -0.0001

Data Index: 1229652 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0759. Min Act: -0.0001

Data Index: 162350 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0217. Min Act: -0.0001

Data Index: 429993 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8932. Min Act: -0.0001

Data Index: 87406 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0051. Min Act: -0.0001

Data Index: 735983 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9114. Min Act: -0.0001

Data Index: 574447 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8229. Min Act: -0.0001

Data Index: 298537 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7676. Min Act: -0.0001

Data Index: 1195839 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7323. Min Act: -0.0001

Data Index: 348441 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7451. Min Act: -0.0001

Data Index: 1155444 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7499. Min Act: -0.0001

Data Index: 456327 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7341. Min Act: -0.0001

Data Index: 1282814 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7223. Min Act: -0.0001

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7205. Min Act: -0.0001

Data Index: 263780 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.6826. Min Act: -0.0001

Data Index: 801205 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.6470. Min Act: -0.0001

Data Index: 512853 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.6858. Min Act: -0.0001

Data Index: 514044 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.6850. Min Act: -0.0001

Data Index: 698669 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.6685. Min Act: -0.0001

Data Index: 773829 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.5992. Min Act: -0.0001

Data Index: 1150772 (C4 (Web Text))

Max Activating Token Index: 718