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

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

Neuron 1184 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7216. Min Range: -3.7216

Max Act: 3.5790. Min Act: -0.0001

Data Index: 353129 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 3.7216. Min Range: -3.7216

Max Act: 3.7216. Min Act: -0.0001

Data Index: 1229793 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 3.7216. Min Range: -3.7216

Max Act: 3.2579. Min Act: -0.0001

Data Index: 382300 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 3.7216. Min Range: -3.7216

Max Act: 3.0829. Min Act: -0.0001

Data Index: 1231468 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 3.7216. Min Range: -3.7216

Max Act: 3.0739. Min Act: -0.0001

Data Index: 252626 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.8917. Min Act: -0.0001

Data Index: 176281 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 3.7216. Min Range: -3.7216

Max Act: 3.1063. Min Act: -0.0001

Data Index: 995786 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 3.7216. Min Range: -3.7216

Max Act: 3.1931. Min Act: -0.0001

Data Index: 1143546 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.7445. Min Act: -0.0001

Data Index: 442342 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.8470. Min Act: -0.0001

Data Index: 618568 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.7756. Min Act: -0.0001

Data Index: 409319 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.8928. Min Act: -0.0001

Data Index: 649044 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.9981. Min Act: -0.0001

Data Index: 1166287 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.3364. Min Act: -0.0001

Data Index: 905860 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.3963. Min Act: -0.0001

Data Index: 999512 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.6003. Min Act: -0.0001

Data Index: 116819 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.7264. Min Act: -0.0001

Data Index: 924860 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.3504. Min Act: -0.0001

Data Index: 1336797 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.3063. Min Act: -0.0001

Data Index: 519728 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.6944. Min Act: -0.0001

Data Index: 1006683 (C4 (Web Text))

Max Activating Token Index: 764