Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2491 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1363884 (Python Code)

Max Activating Token Index: 912

Text #1

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3873. Min Act: -0.0000

Data Index: 1050360 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1550782 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3407. Min Act: -0.0000

Data Index: 163493 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3441. Min Act: -0.0000

Data Index: 4894 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3571. Min Act: -0.0000

Data Index: 259218 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1038484 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3076. Min Act: -0.0000

Data Index: 725370 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3067. Min Act: -0.0000

Data Index: 618951 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1276752 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2722. Min Act: -0.0000

Data Index: 850530 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2794. Min Act: -0.0000

Data Index: 529666 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1296449 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2987. Min Act: -0.0000

Data Index: 47884 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2875. Min Act: -0.0000

Data Index: 419305 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1391124 (Python Code)

Max Activating Token Index: 509

Text #16

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1024973 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1118021 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2618. Min Act: -0.0000

Data Index: 735938 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2713. Min Act: -0.0000

Data Index: 531207 (C4 (Web Text))

Max Activating Token Index: 180