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

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

Neuron 3197 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3689. Min Act: -0.0003

Data Index: 1153271 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3460. Min Act: -0.0003

Data Index: 275661 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3230. Min Act: -0.0003

Data Index: 1238550 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3077. Min Act: -0.0003

Data Index: 674821 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2935. Min Act: -0.0003

Data Index: 119134 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3004. Min Act: -0.0003

Data Index: 1214319 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2863. Min Act: -0.0003

Data Index: 1204875 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2998. Min Act: -0.0002

Data Index: 1071280 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2893. Min Act: -0.0003

Data Index: 1356462 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2900. Min Act: -0.0003

Data Index: 309796 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2964. Min Act: -0.0003

Data Index: 739610 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2783. Min Act: -0.0003

Data Index: 216333 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2718. Min Act: -0.0003

Data Index: 1262165 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2793. Min Act: -0.0003

Data Index: 911988 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2920. Min Act: -0.0003

Data Index: 35797 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2878. Min Act: -0.0003

Data Index: 1081187 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2762. Min Act: -0.0003

Data Index: 1336277 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2817. Min Act: -0.0003

Data Index: 114700 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2715. Min Act: -0.0003

Data Index: 1082626 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2704. Min Act: -0.0003

Data Index: 315393 (C4 (Web Text))

Max Activating Token Index: 927