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

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

Neuron 3 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.8937. Min Act: -0.0000

Data Index: 953525 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1325328 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.7563. Min Act: -0.0000

Data Index: 954620 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6863. Min Act: -0.0000

Data Index: 107023 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6411. Min Act: -0.0000

Data Index: 30943 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6181. Min Act: -0.0000

Data Index: 571250 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6448. Min Act: -0.0000

Data Index: 810213 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6163. Min Act: -0.0000

Data Index: 373305 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5896. Min Act: -0.0000

Data Index: 67820 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1142440 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5927. Min Act: -0.0000

Data Index: 676182 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5662. Min Act: -0.0000

Data Index: 491907 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1063861 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1176407 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5709. Min Act: 0.0000

Data Index: 1040973 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5669. Min Act: -0.0000

Data Index: 685395 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5691. Min Act: -0.0000

Data Index: 647519 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5411. Min Act: -0.0000

Data Index: 501747 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5575. Min Act: -0.0000

Data Index: 481374 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1114655 (C4 (Web Text))

Max Activating Token Index: 633