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

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

Neuron 5226 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5973. Min Range: -5.5973

Max Act: 5.5973. Min Act: -0.0000

Data Index: 1284063 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 5.5973. Min Range: -5.5973

Max Act: 5.4106. Min Act: -0.0000

Data Index: 834871 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 5.5973. Min Range: -5.5973

Max Act: 5.5964. Min Act: -0.0000

Data Index: 114786 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 5.5973. Min Range: -5.5973

Max Act: 5.1978. Min Act: -0.0000

Data Index: 1136480 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 5.5973. Min Range: -5.5973

Max Act: 5.2803. Min Act: -0.0000

Data Index: 1013767 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 5.5973. Min Range: -5.5973

Max Act: 5.1838. Min Act: -0.0000

Data Index: 274664 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.9788. Min Act: -0.0000

Data Index: 1312925 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.8376. Min Act: -0.0000

Data Index: 372535 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.7619. Min Act: -0.0000

Data Index: 1356627 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.7648. Min Act: -0.0000

Data Index: 153475 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.9526. Min Act: -0.0000

Data Index: 1004680 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.9183. Min Act: -0.0000

Data Index: 575879 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.6881. Min Act: -0.0000

Data Index: 1109280 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.6636. Min Act: -0.0000

Data Index: 1210278 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.7951. Min Act: -0.0000

Data Index: 840748 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.7299. Min Act: -0.0000

Data Index: 783300 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.4984. Min Act: -0.0000

Data Index: 1117139 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.4618. Min Act: -0.0000

Data Index: 345552 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.2569. Min Act: -0.0000

Data Index: 777635 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 5.5973. Min Range: -5.5973

Max Act: 4.3752. Min Act: -0.0000

Data Index: 218376 (C4 (Web Text))

Max Activating Token Index: 128