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

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

Neuron 3523 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: 0.2615. Min Range: -0.2615

Max Act: 0.2615. Min Act: -0.0000

Data Index: 379698 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.2446. Min Act: -0.0000

Data Index: 138410 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.2107. Min Act: -0.0000

Data Index: 80566 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1975. Min Act: -0.0000

Data Index: 444963 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.2168. Min Act: -0.0000

Data Index: 272604 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.2007. Min Act: -0.0000

Data Index: 21343 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1320441 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.2067. Min Act: -0.0000

Data Index: 950139 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.2066. Min Act: -0.0000

Data Index: 698574 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1867. Min Act: -0.0000

Data Index: 21156 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1231486 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1793. Min Act: -0.0000

Data Index: 439900 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1836. Min Act: -0.0000

Data Index: 368541 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1895. Min Act: -0.0000

Data Index: 284394 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.2034. Min Act: -0.0000

Data Index: 733466 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1744. Min Act: -0.0000

Data Index: 31511 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1959. Min Act: -0.0000

Data Index: 92278 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1907. Min Act: -0.0000

Data Index: 765903 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1189679 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.2615. Min Range: -0.2615

Max Act: 0.1736. Min Act: -0.0000

Data Index: 993550 (C4 (Web Text))

Max Activating Token Index: 104