Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 946 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5591. Min Act: -0.0002

Data Index: 176551 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5078. Min Act: -0.0001

Data Index: 500886 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4663. Min Act: -0.0002

Data Index: 691575 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4840. Min Act: -0.0001

Data Index: 708711 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4785. Min Act: -0.0002

Data Index: 728088 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4609. Min Act: -0.0002

Data Index: 1316174 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4582. Min Act: -0.0001

Data Index: 893468 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1276349 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4650. Min Act: -0.0001

Data Index: 323038 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4780. Min Act: -0.0002

Data Index: 1204184 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4481. Min Act: -0.0002

Data Index: 819079 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4572. Min Act: -0.0001

Data Index: 727352 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4150. Min Act: -0.0001

Data Index: 889964 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4527. Min Act: -0.0001

Data Index: 1313096 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4686. Min Act: -0.0002

Data Index: 445635 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4396. Min Act: -0.0002

Data Index: 1181434 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4538. Min Act: -0.0001

Data Index: 1285128 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4318. Min Act: -0.0001

Data Index: 573441 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4578. Min Act: -0.0002

Data Index: 813958 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4320. Min Act: -0.0002

Data Index: 392317 (C4 (Web Text))

Max Activating Token Index: 954