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

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

Neuron 4300 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: 0.1166. Min Range: -0.1166

Max Act: 0.1166. Min Act: -0.0002

Data Index: 700436 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1106. Min Act: -0.0002

Data Index: 231071 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0985. Min Act: -0.0002

Data Index: 283514 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1656300 (Python Code)

Max Activating Token Index: 659

Text #4

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1025158 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0846. Min Act: -0.0002

Data Index: 920370 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0868. Min Act: -0.0002

Data Index: 980284 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0837. Min Act: -0.0002

Data Index: 445020 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0782. Min Act: -0.0002

Data Index: 334341 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0841. Min Act: -0.0002

Data Index: 59133 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0802. Min Act: -0.0002

Data Index: 228592 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0752. Min Act: -0.0002

Data Index: 767585 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0752. Min Act: -0.0002

Data Index: 71220 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0756. Min Act: -0.0002

Data Index: 449755 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0717. Min Act: -0.0002

Data Index: 141298 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1543254 (Python Code)

Max Activating Token Index: 240

Text #16

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1426128 (Python Code)

Max Activating Token Index: 889

Text #17

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1412813 (Python Code)

Max Activating Token Index: 93

Text #18

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0727. Min Act: -0.0002

Data Index: 586646 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0724. Min Act: -0.0002

Data Index: 527979 (C4 (Web Text))

Max Activating Token Index: 755