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

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

Neuron 1260 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.9341. Min Act: -0.0000

Data Index: 759843 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.8860. Min Act: -0.0000

Data Index: 54892 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7611. Min Act: -0.0000

Data Index: 218449 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7692. Min Act: -0.0000

Data Index: 416586 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1190160 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7582. Min Act: -0.0000

Data Index: 633383 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7272. Min Act: -0.0000

Data Index: 180585 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1025181 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1334087 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6545. Min Act: -0.0000

Data Index: 607661 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1208416 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6562. Min Act: -0.0000

Data Index: 759540 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6311. Min Act: -0.0000

Data Index: 630813 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6403. Min Act: -0.0000

Data Index: 682289 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6539. Min Act: -0.0000

Data Index: 21034 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.5791. Min Act: -0.0000

Data Index: 567401 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6198. Min Act: -0.0000

Data Index: 452399 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6102. Min Act: -0.0000

Data Index: 520434 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6025. Min Act: -0.0000

Data Index: 348087 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1331527 (C4 (Web Text))

Max Activating Token Index: 725