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

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

Neuron 181 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1523244 (Python Code)

Max Activating Token Index: 716

Text #1

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.9422. Min Act: -0.0000

Data Index: 735929 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.9404. Min Act: -0.0000

Data Index: 417247 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.9067. Min Act: -0.0000

Data Index: 700988 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8750. Min Act: 0.0000

Data Index: 736504 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8630. Min Act: 0.0000

Data Index: 252542 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8652. Min Act: -0.0000

Data Index: 376863 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1391434 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1500777 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7685. Min Act: -0.0000

Data Index: 234553 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1029526 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1361503 (Python Code)

Max Activating Token Index: 783

Text #12

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7261. Min Act: 0.0000

Data Index: 1275223 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7208. Min Act: -0.0000

Data Index: 212286 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7172. Min Act: -0.0000

Data Index: 12446 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7435. Min Act: 0.0000

Data Index: 410963 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1157191 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1169110 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7141. Min Act: -0.0000

Data Index: 530667 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1429896 (Python Code)

Max Activating Token Index: 497