Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 440 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1154. Min Act: -0.0002

Data Index: 766276 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1098. Min Act: -0.0002

Data Index: 404898 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1013. Min Act: -0.0002

Data Index: 492418 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1050. Min Act: -0.0002

Data Index: 233581 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0929. Min Act: -0.0002

Data Index: 742463 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1204149 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0964. Min Act: -0.0002

Data Index: 581113 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0955. Min Act: -0.0002

Data Index: 504473 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0954. Min Act: -0.0002

Data Index: 691631 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0979. Min Act: -0.0002

Data Index: 174458 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0922. Min Act: -0.0002

Data Index: 214709 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1071067 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0910. Min Act: -0.0002

Data Index: 620223 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0897. Min Act: -0.0002

Data Index: 864793 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1221282 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0869. Min Act: -0.0002

Data Index: 85088 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0861. Min Act: -0.0002

Data Index: 512239 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0853. Min Act: -0.0002

Data Index: 309727 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0886. Min Act: -0.0002

Data Index: 150083 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0897. Min Act: -0.0002

Data Index: 848872 (C4 (Web Text))

Max Activating Token Index: 176