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

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

Neuron 2951 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1317173 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0914. Min Act: -0.0001

Data Index: 246658 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1345517 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0838. Min Act: -0.0001

Data Index: 659267 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0839. Min Act: -0.0001

Data Index: 75770 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0739. Min Act: -0.0001

Data Index: 372336 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0862. Min Act: -0.0001

Data Index: 740363 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0860. Min Act: -0.0001

Data Index: 907603 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0744. Min Act: -0.0001

Data Index: 141594 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0806. Min Act: -0.0001

Data Index: 261005 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0760. Min Act: -0.0001

Data Index: 722989 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1471039 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1045781 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0616. Min Act: -0.0001

Data Index: 443814 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0555. Min Act: -0.0001

Data Index: 612160 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1477959 (Python Code)

Max Activating Token Index: 482

Text #16

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1584346 (Python Code)

Max Activating Token Index: 494

Text #17

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1400957 (Python Code)

Max Activating Token Index: 282

Text #18

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1405796 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1548559 (Python Code)

Max Activating Token Index: 594