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

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

Neuron 1923 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1136839 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.2384. Min Act: -0.0000

Data Index: 68290 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.2656. Min Act: -0.0000

Data Index: 796532 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1093849 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.2098. Min Act: -0.0000

Data Index: 870535 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.1345. Min Act: -0.0000

Data Index: 581416 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.1812. Min Act: -0.0000

Data Index: 906992 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1264394 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.1000. Min Act: -0.0000

Data Index: 539090 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1021699 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0668. Min Act: -0.0000

Data Index: 705543 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0812. Min Act: -0.0000

Data Index: 18764 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0485. Min Act: -0.0000

Data Index: 17161 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0393. Min Act: -0.0000

Data Index: 399266 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1168448 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1156752 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0409. Min Act: -0.0000

Data Index: 225821 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0344. Min Act: -0.0000

Data Index: 658212 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0137. Min Act: -0.0000

Data Index: 898157 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0399. Min Act: -0.0000

Data Index: 1120553 (C4 (Web Text))

Max Activating Token Index: 581