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

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

Neuron 968 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: 2.4498. Min Range: -2.4498

Max Act: 2.4498. Min Act: -0.0000

Data Index: 1454679 (Python Code)

Max Activating Token Index: 855

Text #1

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.2845. Min Act: -0.0000

Data Index: 1646687 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.2084. Min Act: -0.0000

Data Index: 1413255 (Python Code)

Max Activating Token Index: 844

Text #3

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.3155. Min Act: -0.0001

Data Index: 1410374 (Python Code)

Max Activating Token Index: 841

Text #4

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.3115. Min Act: -0.0000

Data Index: 1526975 (Python Code)

Max Activating Token Index: 461

Text #5

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.2819. Min Act: -0.0000

Data Index: 1624553 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.3774. Min Act: -0.0000

Data Index: 1471108 (Python Code)

Max Activating Token Index: 998

Text #7

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.1331. Min Act: -0.0000

Data Index: 1637721 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.2437. Min Act: -0.0000

Data Index: 1435220 (Python Code)

Max Activating Token Index: 152

Text #9

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.3165. Min Act: -0.0000

Data Index: 1484286 (Python Code)

Max Activating Token Index: 985

Text #10

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.0803. Min Act: -0.0000

Data Index: 1643074 (Python Code)

Max Activating Token Index: 270

Text #11

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.3220. Min Act: -0.0000

Data Index: 1627816 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.1963. Min Act: -0.0000

Data Index: 1622770 (Python Code)

Max Activating Token Index: 708

Text #13

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.3237. Min Act: -0.0000

Data Index: 1554375 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.1684. Min Act: -0.0000

Data Index: 1373729 (Python Code)

Max Activating Token Index: 1012

Text #15

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.0439. Min Act: -0.0000

Data Index: 1546864 (Python Code)

Max Activating Token Index: 954

Text #16

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.1578. Min Act: -0.0000

Data Index: 1490758 (Python Code)

Max Activating Token Index: 147

Text #17

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.0986. Min Act: -0.0000

Data Index: 1449630 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.1479. Min Act: -0.0000

Data Index: 1540292 (Python Code)

Max Activating Token Index: 48

Text #19

Max Range: 2.4498. Min Range: -2.4498

Max Act: 2.2536. Min Act: -0.0000

Data Index: 1650555 (Python Code)

Max Activating Token Index: 752