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

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

Neuron 3844 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2327. Min Act: -0.0000

Data Index: 392286 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1316450 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2216. Min Act: -0.0001

Data Index: 746033 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2259. Min Act: -0.0001

Data Index: 1194060 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2025. Min Act: -0.0000

Data Index: 50671 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2293. Min Act: -0.0001

Data Index: 47964 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2208. Min Act: -0.0001

Data Index: 396469 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2187. Min Act: -0.0000

Data Index: 160897 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1340019 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2246. Min Act: -0.0000

Data Index: 563810 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1717. Min Act: -0.0001

Data Index: 1314278 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1409113 (Python Code)

Max Activating Token Index: 999

Text #12

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2047. Min Act: -0.0001

Data Index: 738158 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1741. Min Act: -0.0000

Data Index: 727399 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1785. Min Act: -0.0000

Data Index: 361884 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1805. Min Act: -0.0000

Data Index: 927558 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1672. Min Act: -0.0000

Data Index: 899267 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1945. Min Act: -0.0001

Data Index: 1293020 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1922. Min Act: -0.0001

Data Index: 603864 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1825. Min Act: -0.0001

Data Index: 772700 (C4 (Web Text))

Max Activating Token Index: 375