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

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

Neuron 1822 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.8961. Min Act: -0.0000

Data Index: 1635715 (Python Code)

Max Activating Token Index: 620

Text #1

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.9823. Min Act: -0.0000

Data Index: 1455860 (Python Code)

Max Activating Token Index: 297

Text #2

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.7644. Min Act: -0.0000

Data Index: 1364462 (Python Code)

Max Activating Token Index: 649

Text #3

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.6985. Min Act: -0.0000

Data Index: 1553374 (Python Code)

Max Activating Token Index: 653

Text #4

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.6953. Min Act: 0.0000

Data Index: 1562564 (Python Code)

Max Activating Token Index: 885

Text #5

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.6915. Min Act: -0.0000

Data Index: 1373776 (Python Code)

Max Activating Token Index: 567

Text #6

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.5539. Min Act: -0.0000

Data Index: 1363753 (Python Code)

Max Activating Token Index: 326

Text #7

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.6312. Min Act: -0.0000

Data Index: 1530569 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1501103 (Python Code)

Max Activating Token Index: 416

Text #9

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.5718. Min Act: -0.0000

Data Index: 1464261 (Python Code)

Max Activating Token Index: 954

Text #10

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.4617. Min Act: -0.0000

Data Index: 1436157 (Python Code)

Max Activating Token Index: 637

Text #11

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.5483. Min Act: -0.0000

Data Index: 1376546 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.4542. Min Act: 0.0000

Data Index: 1614455 (Python Code)

Max Activating Token Index: 927

Text #13

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.6346. Min Act: 0.0000

Data Index: 1593156 (Python Code)

Max Activating Token Index: 916

Text #14

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.4477. Min Act: -0.0000

Data Index: 1539755 (Python Code)

Max Activating Token Index: 1006

Text #15

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.4313. Min Act: -0.0000

Data Index: 1485273 (Python Code)

Max Activating Token Index: 370

Text #16

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.5043. Min Act: 0.0000

Data Index: 1526271 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.4724. Min Act: 0.0000

Data Index: 1625685 (Python Code)

Max Activating Token Index: 189

Text #18

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.4516. Min Act: 0.0000

Data Index: 1480986 (Python Code)

Max Activating Token Index: 469

Text #19

Max Range: 1.9823. Min Range: -1.9823

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1533564 (Python Code)

Max Activating Token Index: 960