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

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

Neuron 4388 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6565. Min Range: -2.6565

Max Act: 2.6565. Min Act: -0.0000

Data Index: 1473781 (Python Code)

Max Activating Token Index: 687

Text #1

Max Range: 2.6565. Min Range: -2.6565

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1504349 (Python Code)

Max Activating Token Index: 434

Text #2

Max Range: 2.6565. Min Range: -2.6565

Max Act: 2.4157. Min Act: -0.0000

Data Index: 1447953 (Python Code)

Max Activating Token Index: 973

Text #3

Max Range: 2.6565. Min Range: -2.6565

Max Act: 2.1836. Min Act: -0.0000

Data Index: 1512258 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 2.6565. Min Range: -2.6565

Max Act: 2.1494. Min Act: -0.0000

Data Index: 1610178 (Python Code)

Max Activating Token Index: 120

Text #5

Max Range: 2.6565. Min Range: -2.6565

Max Act: 2.0469. Min Act: -0.0000

Data Index: 1549669 (Python Code)

Max Activating Token Index: 559

Text #6

Max Range: 2.6565. Min Range: -2.6565

Max Act: 2.0194. Min Act: -0.0000

Data Index: 1519604 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 2.6565. Min Range: -2.6565

Max Act: 2.0037. Min Act: -0.0000

Data Index: 1627376 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.8824. Min Act: -0.0000

Data Index: 1649613 (Python Code)

Max Activating Token Index: 73

Text #9

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.9543. Min Act: -0.0000

Data Index: 1553398 (Python Code)

Max Activating Token Index: 118

Text #10

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.9362. Min Act: -0.0000

Data Index: 1642751 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.9253. Min Act: -0.0000

Data Index: 1482758 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 2.6565. Min Range: -2.6565

Max Act: 2.0217. Min Act: -0.0000

Data Index: 1501815 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.9796. Min Act: -0.0000

Data Index: 1364867 (Python Code)

Max Activating Token Index: 681

Text #14

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.7809. Min Act: -0.0000

Data Index: 1544881 (Python Code)

Max Activating Token Index: 982

Text #15

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.9547. Min Act: -0.0000

Data Index: 1607940 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.8287. Min Act: -0.0000

Data Index: 1430735 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.8139. Min Act: -0.0000

Data Index: 1507761 (Python Code)

Max Activating Token Index: 749

Text #18

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.6886. Min Act: -0.0000

Data Index: 1517065 (Python Code)

Max Activating Token Index: 786

Text #19

Max Range: 2.6565. Min Range: -2.6565

Max Act: 1.7966. Min Act: -0.0000

Data Index: 1446148 (Python Code)

Max Activating Token Index: 530