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

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

Neuron 1197 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1426747 (Python Code)

Max Activating Token Index: 794

Text #1

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1407813 (Python Code)

Max Activating Token Index: 936

Text #2

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1379225 (Python Code)

Max Activating Token Index: 448

Text #3

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1587990 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1516965 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1561039 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1433324 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1557323 (Python Code)

Max Activating Token Index: 919

Text #8

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1388454 (Python Code)

Max Activating Token Index: 351

Text #9

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1405946 (Python Code)

Max Activating Token Index: 734

Text #10

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1638167 (Python Code)

Max Activating Token Index: 228

Text #11

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1484422 (Python Code)

Max Activating Token Index: 932

Text #12

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1379813 (Python Code)

Max Activating Token Index: 636

Text #13

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1503983 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1505962 (Python Code)

Max Activating Token Index: 1020

Text #15

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1582160 (Python Code)

Max Activating Token Index: 339

Text #16

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1475639 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1625201 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1371939 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1372350 (Python Code)

Max Activating Token Index: 101