Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2870 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 9.4109. Min Range: -9.4109

Max Act: 9.4109. Min Act: -0.0000

Data Index: 1576446 (Python Code)

Max Activating Token Index: 608

Text #1

Max Range: 9.4109. Min Range: -9.4109

Max Act: 9.3121. Min Act: -0.0000

Data Index: 1587526 (Python Code)

Max Activating Token Index: 346

Text #2

Max Range: 9.4109. Min Range: -9.4109

Max Act: 9.3135. Min Act: -0.0000

Data Index: 1451720 (Python Code)

Max Activating Token Index: 911

Text #3

Max Range: 9.4109. Min Range: -9.4109

Max Act: 9.2806. Min Act: -0.0000

Data Index: 1460416 (Python Code)

Max Activating Token Index: 449

Text #4

Max Range: 9.4109. Min Range: -9.4109

Max Act: 9.1828. Min Act: -0.0000

Data Index: 1442723 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.9464. Min Act: -0.0000

Data Index: 1554828 (Python Code)

Max Activating Token Index: 849

Text #6

Max Range: 9.4109. Min Range: -9.4109

Max Act: 9.2285. Min Act: -0.0000

Data Index: 1469348 (Python Code)

Max Activating Token Index: 648

Text #7

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.8164. Min Act: -0.0000

Data Index: 1654214 (Python Code)

Max Activating Token Index: 394

Text #8

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.8277. Min Act: -0.0000

Data Index: 1547848 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 9.4109. Min Range: -9.4109

Max Act: 9.0955. Min Act: -0.0000

Data Index: 1573171 (Python Code)

Max Activating Token Index: 793

Text #10

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.9165. Min Act: -0.0000

Data Index: 1430906 (Python Code)

Max Activating Token Index: 816

Text #11

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.7392. Min Act: -0.0000

Data Index: 1611782 (Python Code)

Max Activating Token Index: 350

Text #12

Max Range: 9.4109. Min Range: -9.4109

Max Act: 9.0349. Min Act: -0.0000

Data Index: 1426126 (Python Code)

Max Activating Token Index: 565

Text #13

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.9345. Min Act: -0.0000

Data Index: 1397042 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.7408. Min Act: -0.0000

Data Index: 1562116 (Python Code)

Max Activating Token Index: 887

Text #15

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.7401. Min Act: -0.0000

Data Index: 1498661 (Python Code)

Max Activating Token Index: 587

Text #16

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.7082. Min Act: -0.0000

Data Index: 1602329 (Python Code)

Max Activating Token Index: 896

Text #17

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.7059. Min Act: -0.0000

Data Index: 1449887 (Python Code)

Max Activating Token Index: 142

Text #18

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.5029. Min Act: -0.0000

Data Index: 1577055 (Python Code)

Max Activating Token Index: 384

Text #19

Max Range: 9.4109. Min Range: -9.4109

Max Act: 8.4603. Min Act: -0.0000

Data Index: 1416183 (Python Code)

Max Activating Token Index: 344