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

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

Neuron 3018 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2197. Min Act: -0.0001

Data Index: 145183 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2201. Min Act: -0.0001

Data Index: 1069767 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2122. Min Act: -0.0001

Data Index: 564649 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2191. Min Act: -0.0001

Data Index: 830956 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2006. Min Act: -0.0001

Data Index: 1270327 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1146159 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1897. Min Act: -0.0001

Data Index: 1198383 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1769. Min Act: -0.0001

Data Index: 919773 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1784. Min Act: -0.0001

Data Index: 1328934 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1789. Min Act: -0.0001

Data Index: 930804 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1829. Min Act: -0.0001

Data Index: 525524 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1878. Min Act: -0.0001

Data Index: 704584 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1770. Min Act: -0.0001

Data Index: 975795 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1750. Min Act: -0.0001

Data Index: 376336 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1705. Min Act: -0.0001

Data Index: 1081287 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1330895 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1344748 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1609. Min Act: -0.0001

Data Index: 481057 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1609. Min Act: -0.0001

Data Index: 60536 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1641. Min Act: -0.0001

Data Index: 968527 (C4 (Web Text))

Max Activating Token Index: 953