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

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

Neuron 4290 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1157296 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5087. Min Act: -0.0000

Data Index: 174856 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5072. Min Act: -0.0000

Data Index: 64559 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4182. Min Act: -0.0000

Data Index: 762120 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1032298 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1294944 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3892. Min Act: -0.0000

Data Index: 191707 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3823. Min Act: -0.0000

Data Index: 447870 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1212984 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3982. Min Act: -0.0000

Data Index: 336975 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3966. Min Act: -0.0000

Data Index: 637350 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3739. Min Act: -0.0000

Data Index: 129127 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3916. Min Act: -0.0000

Data Index: 320255 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1018645 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3559. Min Act: -0.0000

Data Index: 68558 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3905. Min Act: -0.0000

Data Index: 271993 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3491. Min Act: -0.0000

Data Index: 756386 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3594. Min Act: -0.0000

Data Index: 379410 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1020726 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1223613 (C4 (Web Text))

Max Activating Token Index: 335