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

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

Neuron 2493 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.8068. Min Act: -0.0002

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6364. Min Act: -0.0002

Data Index: 1643779 (Python Code)

Max Activating Token Index: 706

Text #2

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.4157. Min Act: -0.0003

Data Index: 710261 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.3333. Min Act: -0.0003

Data Index: 169061 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.3087. Min Act: -0.0003

Data Index: 611447 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.3019. Min Act: -0.0003

Data Index: 73637 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.2773. Min Act: -0.0003

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.2953. Min Act: -0.0003

Data Index: 1111099 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.2650. Min Act: -0.0002

Data Index: 1200066 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.2381. Min Act: -0.0002

Data Index: 1562798 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.2185. Min Act: -0.0002

Data Index: 1622014 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.2108. Min Act: -0.0003

Data Index: 1601652 (Python Code)

Max Activating Token Index: 104

Text #12

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.2034. Min Act: -0.0003

Data Index: 1637348 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.2186. Min Act: -0.0002

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.2142. Min Act: -0.0002

Data Index: 1438075 (Python Code)

Max Activating Token Index: 66

Text #15

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.1883. Min Act: -0.0003

Data Index: 1546413 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.1701. Min Act: -0.0002

Data Index: 1483328 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.1690. Min Act: -0.0003

Data Index: 1555412 (Python Code)

Max Activating Token Index: 512

Text #18

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.1794. Min Act: -0.0002

Data Index: 493390 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.1640. Min Act: -0.0002

Data Index: 1625717 (Python Code)

Max Activating Token Index: 992