Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 888 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1192540 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2063. Min Act: -0.0001

Data Index: 1323418 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1035914 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2215. Min Act: -0.0001

Data Index: 546596 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1998. Min Act: -0.0001

Data Index: 516764 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2010. Min Act: 0.0000

Data Index: 249078 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1313583 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1941. Min Act: -0.0001

Data Index: 312380 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1990. Min Act: -0.0001

Data Index: 129573 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1257818 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1878. Min Act: -0.0001

Data Index: 1276945 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1908. Min Act: -0.0001

Data Index: 1236668 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1821. Min Act: -0.0001

Data Index: 715342 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1001521 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1755. Min Act: -0.0001

Data Index: 1096482 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1251046 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1146829 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1774. Min Act: -0.0000

Data Index: 331526 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1763. Min Act: -0.0000

Data Index: 830071 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1786. Min Act: -0.0000

Data Index: 614763 (C4 (Web Text))

Max Activating Token Index: 554