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

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

Neuron 2243 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: 0.9841. Min Range: -0.9841

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1496178 (Python Code)

Max Activating Token Index: 318

Text #1

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8719. Min Act: -0.0000

Data Index: 232217 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1143089 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1409203 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1599088 (Python Code)

Max Activating Token Index: 503

Text #5

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.7365. Min Act: -0.0000

Data Index: 722962 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1507270 (Python Code)

Max Activating Token Index: 336

Text #7

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1484553 (Python Code)

Max Activating Token Index: 879

Text #8

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6854. Min Act: -0.0000

Data Index: 536809 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1535902 (Python Code)

Max Activating Token Index: 955

Text #10

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.7124. Min Act: -0.0000

Data Index: 721325 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6020. Min Act: -0.0000

Data Index: 668135 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1408657 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.7144. Min Act: -0.0000

Data Index: 41538 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6680. Min Act: -0.0000

Data Index: 916512 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1631329 (Python Code)

Max Activating Token Index: 562

Text #16

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6860. Min Act: -0.0000

Data Index: 562825 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6592. Min Act: -0.0000

Data Index: 702944 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1410342 (Python Code)

Max Activating Token Index: 806

Text #19

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1577367 (Python Code)

Max Activating Token Index: 483