Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1075 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2639. Min Act: -0.0001

Data Index: 1233976 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1011477 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1322673 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2403. Min Act: -0.0000

Data Index: 714273 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2444. Min Act: -0.0000

Data Index: 740501 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2416. Min Act: -0.0000

Data Index: 945957 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2170. Min Act: -0.0001

Data Index: 386135 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2059. Min Act: -0.0001

Data Index: 849964 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1358869 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1289012 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1075520 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1017230 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1854. Min Act: -0.0000

Data Index: 260801 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1134145 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1826. Min Act: -0.0000

Data Index: 269402 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1816. Min Act: -0.0000

Data Index: 253274 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1594. Min Act: -0.0000

Data Index: 898161 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1727. Min Act: -0.0000

Data Index: 505390 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1722. Min Act: -0.0000

Data Index: 41929 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1659. Min Act: -0.0001

Data Index: 251479 (C4 (Web Text))

Max Activating Token Index: 609