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

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

Neuron 2252 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.5462. Min Act: -0.0000

Data Index: 187841 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.5358. Min Act: -0.0000

Data Index: 56850 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.5177. Min Act: -0.0000

Data Index: 678810 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1283059 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4548. Min Act: -0.0000

Data Index: 71938 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4708. Min Act: -0.0000

Data Index: 878653 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3972. Min Act: -0.0000

Data Index: 610024 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4141. Min Act: -0.0000

Data Index: 484033 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4060. Min Act: -0.0000

Data Index: 640887 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3926. Min Act: -0.0000

Data Index: 124533 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3927. Min Act: -0.0000

Data Index: 750418 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3653. Min Act: -0.0000

Data Index: 883110 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3740. Min Act: -0.0000

Data Index: 236196 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3794. Min Act: -0.0000

Data Index: 410065 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1026311 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1087252 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1056945 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3583. Min Act: -0.0000

Data Index: 639064 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3745. Min Act: -0.0000

Data Index: 923911 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3844. Min Act: -0.0000

Data Index: 770168 (C4 (Web Text))

Max Activating Token Index: 705