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

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

Neuron 984 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1428097 (Python Code)

Max Activating Token Index: 623

Text #1

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1296566 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.7473. Min Act: -0.0000

Data Index: 307196 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.7733. Min Act: -0.0000

Data Index: 136758 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6517. Min Act: -0.0000

Data Index: 680594 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6609. Min Act: -0.0000

Data Index: 76289 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6722. Min Act: -0.0000

Data Index: 359545 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5660. Min Act: -0.0000

Data Index: 637041 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5973. Min Act: -0.0000

Data Index: 843993 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1129997 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1498805 (Python Code)

Max Activating Token Index: 871

Text #11

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6123. Min Act: -0.0000

Data Index: 278053 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1193130 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1186690 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5825. Min Act: -0.0000

Data Index: 218166 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5336. Min Act: -0.0000

Data Index: 715860 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1149218 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5632. Min Act: -0.0000

Data Index: 820522 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5526. Min Act: -0.0000

Data Index: 850736 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5725. Min Act: -0.0000

Data Index: 51440 (C4 (Web Text))

Max Activating Token Index: 870