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

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

Neuron 4256 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3421. Min Range: -2.3421

Max Act: 2.3421. Min Act: -0.0000

Data Index: 1243126 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 2.3421. Min Range: -2.3421

Max Act: 2.3365. Min Act: -0.0000

Data Index: 560591 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 2.3421. Min Range: -2.3421

Max Act: 2.3041. Min Act: -0.0000

Data Index: 851357 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.9768. Min Act: -0.0000

Data Index: 119799 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 2.3421. Min Range: -2.3421

Max Act: 2.1545. Min Act: -0.0000

Data Index: 94504 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.9337. Min Act: -0.0000

Data Index: 1036012 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.8237. Min Act: -0.0001

Data Index: 265204 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.6980. Min Act: -0.0000

Data Index: 1014465 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 2.3421. Min Range: -2.3421

Max Act: 2.1009. Min Act: -0.0000

Data Index: 695859 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.7628. Min Act: -0.0000

Data Index: 1059766 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.7248. Min Act: -0.0000

Data Index: 667334 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.7219. Min Act: -0.0000

Data Index: 1242322 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.7981. Min Act: -0.0000

Data Index: 150309 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.7051. Min Act: -0.0001

Data Index: 672091 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.9586. Min Act: -0.0000

Data Index: 52929 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.6533. Min Act: -0.0000

Data Index: 202377 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.7368. Min Act: -0.0000

Data Index: 1139406 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.7399. Min Act: -0.0001

Data Index: 29380 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.7275. Min Act: -0.0000

Data Index: 253867 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 2.3421. Min Range: -2.3421

Max Act: 1.7262. Min Act: -0.0000

Data Index: 37549 (C4 (Web Text))

Max Activating Token Index: 626