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

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

Neuron 396 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.3063. Min Act: -0.0000

Data Index: 849710 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.2575. Min Act: -0.0001

Data Index: 870460 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.1630. Min Act: -0.0001

Data Index: 841583 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.1041. Min Act: -0.0001

Data Index: 1057851 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1223636 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.1417. Min Act: -0.0001

Data Index: 277274 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.1254. Min Act: -0.0001

Data Index: 104272 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.0740. Min Act: -0.0001

Data Index: 1178645 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1292471 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.0358. Min Act: -0.0001

Data Index: 1140341 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.0570. Min Act: -0.0001

Data Index: 754242 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9992. Min Act: -0.0001

Data Index: 339632 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.0075. Min Act: -0.0001

Data Index: 780538 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9716. Min Act: -0.0001

Data Index: 1147056 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.0047. Min Act: -0.0001

Data Index: 297795 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9519. Min Act: -0.0001

Data Index: 1174724 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 1.3063. Min Range: -1.3063

Max Act: 1.0056. Min Act: -0.0001

Data Index: 632267 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1017905 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9518. Min Act: -0.0001

Data Index: 164906 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 1.3063. Min Range: -1.3063

Max Act: 0.9750. Min Act: -0.0001

Data Index: 1026368 (C4 (Web Text))

Max Activating Token Index: 874