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

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

Neuron 5535 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: 2.1897. Min Range: -2.1897

Max Act: 2.0607. Min Act: -0.0000

Data Index: 1273148 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.1897. Min Act: -0.0000

Data Index: 432794 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0500. Min Act: -0.0000

Data Index: 348964 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 2.1897. Min Range: -2.1897

Max Act: 2.0718. Min Act: -0.0000

Data Index: 1008593 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.8843. Min Act: -0.0000

Data Index: 92415 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.7121. Min Act: -0.0000

Data Index: 1166413 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.8588. Min Act: -0.0000

Data Index: 136385 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.7507. Min Act: -0.0000

Data Index: 732094 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.7223. Min Act: -0.0000

Data Index: 1179363 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.5597. Min Act: -0.0000

Data Index: 865312 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.5478. Min Act: -0.0000

Data Index: 1056067 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.6087. Min Act: -0.0000

Data Index: 999354 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.6090. Min Act: -0.0000

Data Index: 536859 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.6489. Min Act: -0.0000

Data Index: 691725 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.5005. Min Act: -0.0000

Data Index: 100182 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.3847. Min Act: -0.0000

Data Index: 227085 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.4289. Min Act: -0.0000

Data Index: 12733 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.3157. Min Act: -0.0000

Data Index: 549313 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1134964 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 2.1897. Min Range: -2.1897

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1121872 (C4 (Web Text))

Max Activating Token Index: 247