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

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

Neuron 1890 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1144517 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5596. Min Act: -0.0000

Data Index: 643068 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5158. Min Act: -0.0000

Data Index: 781078 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4945. Min Act: -0.0000

Data Index: 400821 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1140009 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4549. Min Act: -0.0000

Data Index: 304994 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1340698 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4630. Min Act: -0.0000

Data Index: 710765 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4558. Min Act: -0.0000

Data Index: 317699 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1263869 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4606. Min Act: -0.0000

Data Index: 382843 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4368. Min Act: -0.0000

Data Index: 694573 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4355. Min Act: -0.0000

Data Index: 830190 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1358502 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1138337 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1183541 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4275. Min Act: -0.0000

Data Index: 604540 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1055206 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4244. Min Act: -0.0000

Data Index: 618582 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.3984. Min Act: -0.0000

Data Index: 683 (C4 (Web Text))

Max Activating Token Index: 647