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

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

Neuron 3390 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: 6.0973. Min Range: -6.0973

Max Act: 6.0973. Min Act: -0.0000

Data Index: 604536 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 6.0973. Min Range: -6.0973

Max Act: 5.9561. Min Act: -0.0001

Data Index: 331462 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 6.0973. Min Range: -6.0973

Max Act: 5.9277. Min Act: -0.0001

Data Index: 213075 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 6.0973. Min Range: -6.0973

Max Act: 5.6211. Min Act: -0.0001

Data Index: 870301 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 6.0973. Min Range: -6.0973

Max Act: 5.0799. Min Act: -0.0000

Data Index: 116406 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 6.0973. Min Range: -6.0973

Max Act: 5.1178. Min Act: -0.0001

Data Index: 38998 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 6.0973. Min Range: -6.0973

Max Act: 5.0147. Min Act: -0.0001

Data Index: 816676 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.6632. Min Act: -0.0001

Data Index: 697766 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.7965. Min Act: -0.0001

Data Index: 1179293 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.9264. Min Act: -0.0001

Data Index: 726364 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.4560. Min Act: -0.0001

Data Index: 100407 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.6095. Min Act: -0.0001

Data Index: 482325 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.7809. Min Act: -0.0001

Data Index: 402127 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.7179. Min Act: -0.0001

Data Index: 1105799 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.5051. Min Act: -0.0000

Data Index: 34922 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.4736. Min Act: -0.0000

Data Index: 1121813 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.2202. Min Act: -0.0000

Data Index: 739799 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.3800. Min Act: -0.0001

Data Index: 373062 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.3619. Min Act: -0.0001

Data Index: 49966 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 6.0973. Min Range: -6.0973

Max Act: 4.2102. Min Act: -0.0001

Data Index: 740715 (C4 (Web Text))

Max Activating Token Index: 516