Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2288 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.1041. Min Act: -0.0002

Data Index: 485127 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.1023. Min Act: -0.0002

Data Index: 318600 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0952. Min Act: -0.0002

Data Index: 157152 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0788. Min Act: -0.0002

Data Index: 638404 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0816. Min Act: -0.0002

Data Index: 211958 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0798. Min Act: -0.0002

Data Index: 104221 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1009508 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0817. Min Act: -0.0002

Data Index: 135252 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0854. Min Act: -0.0002

Data Index: 188406 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0791. Min Act: -0.0002

Data Index: 481051 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1200723 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0696. Min Act: -0.0002

Data Index: 193085 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1261033 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0668. Min Act: -0.0002

Data Index: 319326 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1359409 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0718. Min Act: -0.0002

Data Index: 945533 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0762. Min Act: -0.0002

Data Index: 711061 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0831. Min Act: -0.0002

Data Index: 475509 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0789. Min Act: -0.0002

Data Index: 602302 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1329289 (C4 (Web Text))

Max Activating Token Index: 291