Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 660 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0002

Data Index: 585910 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0467. Min Act: -0.0003

Data Index: 302088 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0471. Min Act: -0.0003

Data Index: 566050 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0429. Min Act: -0.0003

Data Index: 943687 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0429. Min Act: -0.0003

Data Index: 774976 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0416. Min Act: -0.0002

Data Index: 51919 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0408. Min Act: -0.0003

Data Index: 109837 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0406. Min Act: -0.0002

Data Index: 951060 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0414. Min Act: -0.0003

Data Index: 41898 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1159090 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1129261 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0410. Min Act: -0.0003

Data Index: 894663 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0410. Min Act: -0.0003

Data Index: 106327 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0406. Min Act: -0.0003

Data Index: 175350 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0400. Min Act: -0.0003

Data Index: 327017 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1321935 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1133162 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0396. Min Act: -0.0003

Data Index: 786757 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0394. Min Act: -0.0003

Data Index: 505715 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0389. Min Act: -0.0003

Data Index: 775693 (C4 (Web Text))

Max Activating Token Index: 186