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

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

Neuron 3077 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: 4.1711. Min Range: -4.1711

Max Act: 4.1711. Min Act: 0.0000

Data Index: 1152114 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 4.1711. Min Range: -4.1711

Max Act: 3.4994. Min Act: -0.0000

Data Index: 841629 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 4.1711. Min Range: -4.1711

Max Act: 3.0601. Min Act: -0.0000

Data Index: 459289 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 4.1711. Min Range: -4.1711

Max Act: 3.1748. Min Act: -0.0000

Data Index: 177476 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 4.1711. Min Range: -4.1711

Max Act: 3.2878. Min Act: -0.0000

Data Index: 1079100 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.9860. Min Act: -0.0000

Data Index: 625400 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.9847. Min Act: -0.0000

Data Index: 1287311 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 4.1711. Min Range: -4.1711

Max Act: 3.1078. Min Act: -0.0000

Data Index: 304607 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 4.1711. Min Range: -4.1711

Max Act: 3.0829. Min Act: -0.0000

Data Index: 733848 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.9434. Min Act: -0.0000

Data Index: 939453 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.9139. Min Act: -0.0000

Data Index: 320305 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.8823. Min Act: -0.0000

Data Index: 940240 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.9663. Min Act: -0.0000

Data Index: 398488 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.9246. Min Act: -0.0000

Data Index: 585507 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.6563. Min Act: -0.0000

Data Index: 416019 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.9214. Min Act: -0.0000

Data Index: 185733 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.7811. Min Act: -0.0000

Data Index: 678913 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.7634. Min Act: -0.0000

Data Index: 277780 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.9853. Min Act: -0.0000

Data Index: 1196736 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 4.1711. Min Range: -4.1711

Max Act: 2.8260. Min Act: -0.0000

Data Index: 1291972 (C4 (Web Text))

Max Activating Token Index: 722