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

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

Neuron 1 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3759. Min Range: -2.3759

Max Act: 2.3759. Min Act: -0.0000

Data Index: 665441 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 2.3759. Min Range: -2.3759

Max Act: 2.2145. Min Act: -0.0000

Data Index: 1448840 (Python Code)

Max Activating Token Index: 838

Text #2

Max Range: 2.3759. Min Range: -2.3759

Max Act: 2.1360. Min Act: -0.0000

Data Index: 1490926 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 2.3759. Min Range: -2.3759

Max Act: 2.0682. Min Act: -0.0000

Data Index: 1380699 (Python Code)

Max Activating Token Index: 980

Text #4

Max Range: 2.3759. Min Range: -2.3759

Max Act: 2.0457. Min Act: -0.0000

Data Index: 1587160 (Python Code)

Max Activating Token Index: 854

Text #5

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.8479. Min Act: -0.0000

Data Index: 1466145 (Python Code)

Max Activating Token Index: 825

Text #6

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1645791 (Python Code)

Max Activating Token Index: 750

Text #7

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.8029. Min Act: -0.0000

Data Index: 1651764 (Python Code)

Max Activating Token Index: 477

Text #8

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.7490. Min Act: -0.0000

Data Index: 1399338 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.8204. Min Act: -0.0000

Data Index: 670097 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1454929 (Python Code)

Max Activating Token Index: 461

Text #11

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.6933. Min Act: -0.0000

Data Index: 847585 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.6867. Min Act: -0.0000

Data Index: 1509857 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.5813. Min Act: -0.0000

Data Index: 1360204 (Python Code)

Max Activating Token Index: 945

Text #14

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.6611. Min Act: -0.0000

Data Index: 1477514 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.7595. Min Act: -0.0000

Data Index: 1480758 (Python Code)

Max Activating Token Index: 482

Text #16

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.5439. Min Act: -0.0000

Data Index: 1640057 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1491783 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.5110. Min Act: -0.0000

Data Index: 1525389 (Python Code)

Max Activating Token Index: 300

Text #19

Max Range: 2.3759. Min Range: -2.3759

Max Act: 1.5795. Min Act: -0.0000

Data Index: 1588299 (Python Code)

Max Activating Token Index: 1015