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

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

Neuron 3820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1041279 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8817. Min Act: -0.0000

Data Index: 982938 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8433. Min Act: -0.0000

Data Index: 385735 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8317. Min Act: -0.0000

Data Index: 995916 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8345. Min Act: -0.0000

Data Index: 684569 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7108. Min Act: -0.0000

Data Index: 209330 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7068. Min Act: -0.0000

Data Index: 430125 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7121. Min Act: -0.0000

Data Index: 681362 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1127584 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7112. Min Act: -0.0000

Data Index: 160572 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6415. Min Act: -0.0000

Data Index: 608950 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7098. Min Act: -0.0000

Data Index: 368182 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6908. Min Act: -0.0000

Data Index: 628759 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6989. Min Act: -0.0000

Data Index: 523183 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6956. Min Act: -0.0000

Data Index: 14889 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6680. Min Act: -0.0000

Data Index: 539824 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7042. Min Act: -0.0000

Data Index: 434746 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1239262 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6587. Min Act: -0.0000

Data Index: 191478 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6187. Min Act: -0.0000

Data Index: 882537 (C4 (Web Text))

Max Activating Token Index: 324