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

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

Neuron 2526 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.1128. Min Act: -0.0003

Data Index: 1110503 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.1036. Min Act: -0.0002

Data Index: 666196 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.1027. Min Act: -0.0003

Data Index: 801323 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0987. Min Act: -0.0003

Data Index: 194286 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0984. Min Act: -0.0003

Data Index: 672171 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0964. Min Act: -0.0002

Data Index: 410517 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0974. Min Act: -0.0003

Data Index: 451019 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0937. Min Act: -0.0002

Data Index: 739585 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0935. Min Act: -0.0003

Data Index: 886683 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0923. Min Act: -0.0002

Data Index: 585906 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0914. Min Act: -0.0002

Data Index: 465752 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0914. Min Act: -0.0003

Data Index: 1346 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0905. Min Act: -0.0002

Data Index: 515763 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0903. Min Act: -0.0003

Data Index: 305925 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1301884 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0888. Min Act: -0.0001

Data Index: 518378 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0846. Min Act: -0.0002

Data Index: 599860 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0864. Min Act: -0.0003

Data Index: 80737 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1005789 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0862. Min Act: -0.0002

Data Index: 699530 (C4 (Web Text))

Max Activating Token Index: 842