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

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

Neuron 1591 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3432. Min Range: -2.3432

Max Act: 2.3432. Min Act: -0.0000

Data Index: 356811 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 2.3432. Min Range: -2.3432

Max Act: 2.2407. Min Act: -0.0000

Data Index: 1224087 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 2.3432. Min Range: -2.3432

Max Act: 2.0805. Min Act: -0.0000

Data Index: 1082110 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 2.3432. Min Range: -2.3432

Max Act: 2.0545. Min Act: -0.0000

Data Index: 174292 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.9835. Min Act: -0.0000

Data Index: 97892 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.9549. Min Act: -0.0000

Data Index: 1195847 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.9397. Min Act: -0.0000

Data Index: 1196898 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.9230. Min Act: -0.0000

Data Index: 349722 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.9959. Min Act: -0.0000

Data Index: 921700 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.7928. Min Act: -0.0000

Data Index: 1144951 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.8794. Min Act: -0.0000

Data Index: 934450 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.7590. Min Act: -0.0000

Data Index: 621673 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.8564. Min Act: -0.0000

Data Index: 561093 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.8468. Min Act: -0.0000

Data Index: 484275 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.8443. Min Act: -0.0000

Data Index: 866872 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.7325. Min Act: -0.0000

Data Index: 802390 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.7927. Min Act: -0.0000

Data Index: 334197 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.8992. Min Act: -0.0000

Data Index: 1091286 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.7772. Min Act: -0.0000

Data Index: 190775 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 2.3432. Min Range: -2.3432

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1148296 (C4 (Web Text))

Max Activating Token Index: 67