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

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

Neuron 3963 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0569. Min Act: -0.0002

Data Index: 332815 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0597. Min Act: -0.0002

Data Index: 735524 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0530. Min Act: -0.0002

Data Index: 257244 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1121290 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0560. Min Act: -0.0002

Data Index: 925774 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0580. Min Act: -0.0002

Data Index: 993530 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0603. Min Act: -0.0002

Data Index: 562884 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1426314 (Python Code)

Max Activating Token Index: 957

Text #8

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0504. Min Act: -0.0002

Data Index: 922330 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1152972 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1125816 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1016198 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1224433 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0527. Min Act: -0.0002

Data Index: 45726 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0558. Min Act: -0.0002

Data Index: 116568 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0492. Min Act: -0.0003

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0575. Min Act: -0.0002

Data Index: 405278 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1359519 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1231509 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0475. Min Act: -0.0002

Data Index: 513657 (C4 (Web Text))

Max Activating Token Index: 311