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

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

Neuron 2368 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: 0.1320. Min Range: -0.1320

Max Act: 0.1320. Min Act: -0.0002

Data Index: 90406 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1307254 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1101. Min Act: -0.0002

Data Index: 936845 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1075. Min Act: -0.0002

Data Index: 1256389 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1051221 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0841. Min Act: -0.0002

Data Index: 933737 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0806. Min Act: -0.0002

Data Index: 382900 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0777. Min Act: -0.0002

Data Index: 940112 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0810. Min Act: -0.0002

Data Index: 908428 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1283881 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0773. Min Act: -0.0002

Data Index: 686820 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1332695 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0763. Min Act: -0.0002

Data Index: 122838 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0784. Min Act: -0.0002

Data Index: 766429 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0694. Min Act: -0.0002

Data Index: 642811 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0718. Min Act: -0.0002

Data Index: 739638 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1227701 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0745. Min Act: -0.0002

Data Index: 279012 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0767. Min Act: -0.0002

Data Index: 981274 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0685. Min Act: -0.0002

Data Index: 713716 (C4 (Web Text))

Max Activating Token Index: 747