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

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

Neuron 1958 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.5918. Min Act: -0.0000

Data Index: 379878 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.3679. Min Act: -0.0000

Data Index: 840955 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 2.5918. Min Range: -2.5918

Max Act: 1.9476. Min Act: -0.0000

Data Index: 671640 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.0357. Min Act: -0.0000

Data Index: 455338 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.1358. Min Act: -0.0000

Data Index: 159930 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.1208. Min Act: -0.0000

Data Index: 242897 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.1239. Min Act: -0.0000

Data Index: 658153 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.0875. Min Act: -0.0000

Data Index: 1037750 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 2.5918. Min Range: -2.5918

Max Act: 1.9706. Min Act: -0.0000

Data Index: 335237 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.1595. Min Act: -0.0000

Data Index: 892893 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 2.5918. Min Range: -2.5918

Max Act: 1.9422. Min Act: -0.0000

Data Index: 1271979 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.0498. Min Act: -0.0000

Data Index: 798817 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 2.5918. Min Range: -2.5918

Max Act: 1.9163. Min Act: -0.0000

Data Index: 35512 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.1260. Min Act: -0.0000

Data Index: 671955 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 2.5918. Min Range: -2.5918

Max Act: 2.0802. Min Act: -0.0000

Data Index: 900012 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 2.5918. Min Range: -2.5918

Max Act: 1.8652. Min Act: -0.0000

Data Index: 664776 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 2.5918. Min Range: -2.5918

Max Act: 1.9669. Min Act: -0.0000

Data Index: 612359 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 2.5918. Min Range: -2.5918

Max Act: 1.9474. Min Act: -0.0000

Data Index: 736414 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 2.5918. Min Range: -2.5918

Max Act: 1.9460. Min Act: -0.0000

Data Index: 1083661 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 2.5918. Min Range: -2.5918

Max Act: 1.9232. Min Act: -0.0000

Data Index: 741311 (C4 (Web Text))

Max Activating Token Index: 988