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

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

Neuron 5814 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0860. Min Act: -0.0002

Data Index: 398169 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0794. Min Act: -0.0002

Data Index: 25826 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1131969 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1041126 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0673. Min Act: -0.0002

Data Index: 93229 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0650. Min Act: -0.0002

Data Index: 965869 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0672. Min Act: -0.0002

Data Index: 516890 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0684. Min Act: -0.0002

Data Index: 650299 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0655. Min Act: -0.0002

Data Index: 358057 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0650. Min Act: -0.0002

Data Index: 453103 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0643. Min Act: -0.0002

Data Index: 339624 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1149748 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0662. Min Act: -0.0002

Data Index: 510359 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1258711 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0623. Min Act: -0.0002

Data Index: 292086 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1007220 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0623. Min Act: -0.0002

Data Index: 983544 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1273178 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0583. Min Act: -0.0002

Data Index: 963396 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0603. Min Act: -0.0002

Data Index: 174075 (C4 (Web Text))

Max Activating Token Index: 36