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

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

Neuron 4702 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.9414. Min Act: -0.0000

Data Index: 413014 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7873. Min Act: -0.0000

Data Index: 170288 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7890. Min Act: -0.0000

Data Index: 690205 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6865. Min Act: -0.0000

Data Index: 141516 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6790. Min Act: -0.0000

Data Index: 833893 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6750. Min Act: -0.0000

Data Index: 250129 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6940. Min Act: -0.0000

Data Index: 327898 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1040359 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7004. Min Act: -0.0000

Data Index: 133960 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1057042 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6835. Min Act: -0.0000

Data Index: 934257 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6469. Min Act: -0.0000

Data Index: 985348 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1033248 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6203. Min Act: -0.0000

Data Index: 409863 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6453. Min Act: -0.0000

Data Index: 310384 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6790. Min Act: -0.0000

Data Index: 772056 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1244413 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.5926. Min Act: -0.0000

Data Index: 561622 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.5870. Min Act: -0.0000

Data Index: 228344 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1125235 (C4 (Web Text))

Max Activating Token Index: 70