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

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

Neuron 792 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.8609. Min Act: -0.0000

Data Index: 714363 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.9737. Min Act: -0.0000

Data Index: 1331240 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.7377. Min Act: -0.0000

Data Index: 155969 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.7040. Min Act: -0.0000

Data Index: 347969 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.6376. Min Act: -0.0000

Data Index: 789588 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.5877. Min Act: -0.0000

Data Index: 585563 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.5700. Min Act: -0.0000

Data Index: 759552 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.7667. Min Act: -0.0000

Data Index: 208449 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.8882. Min Act: -0.0000

Data Index: 1184034 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.5662. Min Act: -0.0000

Data Index: 1126974 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.5919. Min Act: -0.0000

Data Index: 97542 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.4071. Min Act: -0.0000

Data Index: 908607 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.5791. Min Act: -0.0000

Data Index: 444296 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.8872. Min Act: -0.0000

Data Index: 1211016 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.7434. Min Act: -0.0000

Data Index: 212129 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.3603. Min Act: -0.0000

Data Index: 253817 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.1900. Min Act: -0.0000

Data Index: 1214299 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.6458. Min Act: -0.0000

Data Index: 708491 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.6150. Min Act: -0.0000

Data Index: 39813 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 8.9737. Min Range: -8.9737

Max Act: 8.2383. Min Act: -0.0000

Data Index: 936326 (C4 (Web Text))

Max Activating Token Index: 857