Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5440 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.5492. Min Act: -0.0000

Data Index: 905224 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.5362. Min Act: -0.0000

Data Index: 65834 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1183319 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1212742 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4577. Min Act: -0.0000

Data Index: 108236 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4218. Min Act: -0.0000

Data Index: 451636 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1145289 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4253. Min Act: -0.0000

Data Index: 173554 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4050. Min Act: -0.0000

Data Index: 961495 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4367. Min Act: -0.0000

Data Index: 835225 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1277764 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3714. Min Act: -0.0000

Data Index: 708118 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1283812 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3663. Min Act: -0.0000

Data Index: 602721 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1253101 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1076866 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3420. Min Act: -0.0000

Data Index: 307960 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3425. Min Act: -0.0000

Data Index: 550664 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3524. Min Act: -0.0000

Data Index: 870114 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3383. Min Act: -0.0000

Data Index: 86168 (C4 (Web Text))

Max Activating Token Index: 463