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

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

Neuron 743 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: 1.2763. Min Range: -1.2763

Max Act: 1.2763. Min Act: -0.0002

Data Index: 663916 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.2091. Min Act: -0.0002

Data Index: 847805 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.2045. Min Act: -0.0002

Data Index: 326676 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0107. Min Act: -0.0002

Data Index: 1255338 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0700. Min Act: -0.0002

Data Index: 1345952 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0419. Min Act: -0.0002

Data Index: 604373 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9943. Min Act: -0.0002

Data Index: 208441 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0864. Min Act: -0.0002

Data Index: 956907 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0492. Min Act: -0.0002

Data Index: 272938 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9878. Min Act: -0.0002

Data Index: 1131356 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0433. Min Act: -0.0002

Data Index: 185511 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9171. Min Act: -0.0002

Data Index: 357128 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9359. Min Act: -0.0002

Data Index: 484247 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.8512. Min Act: -0.0002

Data Index: 590907 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9621. Min Act: -0.0002

Data Index: 142914 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0207. Min Act: -0.0002

Data Index: 337838 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9589. Min Act: -0.0002

Data Index: 1352938 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9929. Min Act: -0.0002

Data Index: 1039090 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9206. Min Act: -0.0002

Data Index: 1094721 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0000. Min Act: -0.0002

Data Index: 115681 (C4 (Web Text))

Max Activating Token Index: 185