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

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

Neuron 1274 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2098. Min Range: -2.2098

Max Act: 2.2098. Min Act: -0.0000

Data Index: 497310 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.6456. Min Act: -0.0000

Data Index: 623843 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1282304 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.6004. Min Act: -0.0000

Data Index: 896955 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.6169. Min Act: -0.0000

Data Index: 137200 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.4967. Min Act: -0.0001

Data Index: 835971 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.5642. Min Act: -0.0000

Data Index: 569779 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.5761. Min Act: -0.0000

Data Index: 1303797 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.4235. Min Act: -0.0001

Data Index: 1037806 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.3011. Min Act: -0.0000

Data Index: 45270 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.1600. Min Act: -0.0001

Data Index: 87576 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.4500. Min Act: -0.0000

Data Index: 1100222 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.3090. Min Act: -0.0000

Data Index: 989815 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.1919. Min Act: -0.0000

Data Index: 951813 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.4658. Min Act: -0.0000

Data Index: 1258622 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.2621. Min Act: -0.0000

Data Index: 292890 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.2998. Min Act: -0.0000

Data Index: 715622 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.2860. Min Act: -0.0000

Data Index: 80043 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.2070. Min Act: -0.0000

Data Index: 234810 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 2.2098. Min Range: -2.2098

Max Act: 1.3220. Min Act: -0.0000

Data Index: 414032 (C4 (Web Text))

Max Activating Token Index: 165