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

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

Neuron 495 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2100. Min Range: -1.2100

Max Act: 1.2100. Min Act: -0.0000

Data Index: 493581 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.2100. Min Range: -1.2100

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1192911 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9295. Min Act: -0.0000

Data Index: 912065 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9604. Min Act: -0.0000

Data Index: 589021 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9114. Min Act: -0.0000

Data Index: 303187 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1393555 (Python Code)

Max Activating Token Index: 904

Text #6

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1132425 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9238. Min Act: -0.0000

Data Index: 988974 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8636. Min Act: -0.0000

Data Index: 284246 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8818. Min Act: -0.0000

Data Index: 770104 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1556192 (Python Code)

Max Activating Token Index: 741

Text #11

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8540. Min Act: -0.0000

Data Index: 883636 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1079669 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8403. Min Act: -0.0000

Data Index: 651542 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1479027 (Python Code)

Max Activating Token Index: 370

Text #15

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8231. Min Act: -0.0000

Data Index: 885612 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1384390 (Python Code)

Max Activating Token Index: 476

Text #17

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1368979 (Python Code)

Max Activating Token Index: 81

Text #18

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7699. Min Act: -0.0000

Data Index: 649751 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1531915 (Python Code)

Max Activating Token Index: 984