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

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

Neuron 4650 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: 1.1058. Min Range: -1.1058

Max Act: 1.1058. Min Act: -0.0000

Data Index: 1172135 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1060242 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.9131. Min Act: -0.0000

Data Index: 798605 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8542. Min Act: -0.0000

Data Index: 760792 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.9139. Min Act: -0.0000

Data Index: 199515 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8933. Min Act: -0.0000

Data Index: 748903 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8621. Min Act: -0.0000

Data Index: 625805 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1248299 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1165255 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8370. Min Act: -0.0000

Data Index: 641388 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8339. Min Act: -0.0000

Data Index: 490991 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8289. Min Act: -0.0000

Data Index: 751929 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7822. Min Act: -0.0000

Data Index: 636997 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7979. Min Act: -0.0000

Data Index: 294150 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7867. Min Act: -0.0000

Data Index: 247916 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7798. Min Act: -0.0000

Data Index: 570476 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7518. Min Act: -0.0000

Data Index: 563216 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7713. Min Act: -0.0000

Data Index: 761910 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7471. Min Act: -0.0000

Data Index: 487827 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7447. Min Act: -0.0000

Data Index: 277192 (C4 (Web Text))

Max Activating Token Index: 583