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

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

Neuron 4291 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.2840. Min Act: -0.0000

Data Index: 747926 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.2208. Min Act: -0.0000

Data Index: 84216 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.1880. Min Act: -0.0000

Data Index: 581033 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.1328. Min Act: -0.0000

Data Index: 1106697 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1036268 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.0903. Min Act: -0.0000

Data Index: 917736 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1273901 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.0148. Min Act: -0.0000

Data Index: 640769 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.0376. Min Act: -0.0000

Data Index: 1168809 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.0008. Min Act: -0.0000

Data Index: 562314 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.0664. Min Act: -0.0000

Data Index: 389074 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 1.2840. Min Range: -1.2840

Max Act: 0.9645. Min Act: -0.0000

Data Index: 407325 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.2840. Min Range: -1.2840

Max Act: 0.9877. Min Act: -0.0000

Data Index: 812718 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 1.2840. Min Range: -1.2840

Max Act: 0.9816. Min Act: -0.0000

Data Index: 341366 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.2840. Min Range: -1.2840

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1210425 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.2840. Min Range: -1.2840

Max Act: 0.9643. Min Act: -0.0000

Data Index: 834360 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.2840. Min Range: -1.2840

Max Act: 0.9582. Min Act: -0.0000

Data Index: 823542 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 1.2840. Min Range: -1.2840

Max Act: 0.9560. Min Act: -0.0000

Data Index: 419782 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.2840. Min Range: -1.2840

Max Act: 0.9615. Min Act: -0.0000

Data Index: 443592 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.2840. Min Range: -1.2840

Max Act: 0.9259. Min Act: -0.0000

Data Index: 268252 (C4 (Web Text))

Max Activating Token Index: 358