Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1831 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0329. Min Act: -0.0002

Data Index: 944991 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0337. Min Act: -0.0002

Data Index: 372542 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 349997 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1315773 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0329. Min Act: -0.0002

Data Index: 842140 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0301. Min Act: -0.0002

Data Index: 379677 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0312. Min Act: -0.0002

Data Index: 285101 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1357384 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0304. Min Act: -0.0002

Data Index: 49634 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0300. Min Act: -0.0002

Data Index: 192803 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1215621 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1175692 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0314. Min Act: -0.0002

Data Index: 626210 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0283. Min Act: -0.0002

Data Index: 952239 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1099093 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1265605 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0315. Min Act: -0.0002

Data Index: 128832 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1090219 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1161716 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0288. Min Act: -0.0002

Data Index: 195803 (C4 (Web Text))

Max Activating Token Index: 171