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

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

Neuron 500 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.2082. Min Act: -0.0002

Data Index: 494217 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1813. Min Act: -0.0002

Data Index: 195434 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1782. Min Act: -0.0002

Data Index: 793439 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1548. Min Act: -0.0002

Data Index: 313122 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1847. Min Act: -0.0002

Data Index: 839759 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1385. Min Act: -0.0002

Data Index: 570166 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1585. Min Act: -0.0002

Data Index: 528334 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1510. Min Act: -0.0002

Data Index: 813916 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1566. Min Act: -0.0002

Data Index: 706244 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1468. Min Act: -0.0002

Data Index: 303677 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1568. Min Act: -0.0002

Data Index: 353935 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1621. Min Act: -0.0002

Data Index: 942576 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1533. Min Act: -0.0002

Data Index: 1147744 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1506. Min Act: -0.0002

Data Index: 588871 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1641. Min Act: -0.0002

Data Index: 1341145 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1587. Min Act: -0.0002

Data Index: 1029858 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1340. Min Act: -0.0002

Data Index: 380599 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1496. Min Act: -0.0002

Data Index: 1178980 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1458. Min Act: -0.0002

Data Index: 771958 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1461. Min Act: -0.0002

Data Index: 672873 (C4 (Web Text))

Max Activating Token Index: 8