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

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

Neuron 4708 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: 0.7502. Min Range: -0.7502

Max Act: 0.7502. Min Act: -0.0000

Data Index: 78507 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.7253. Min Act: 0.0000

Data Index: 668694 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1002974 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6712. Min Act: -0.0000

Data Index: 934979 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6847. Min Act: -0.0000

Data Index: 148654 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1142859 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6455. Min Act: 0.0000

Data Index: 1103585 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6877. Min Act: -0.0000

Data Index: 115593 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6284. Min Act: -0.0000

Data Index: 180073 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1199435 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1207119 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6394. Min Act: -0.0000

Data Index: 538789 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6123. Min Act: -0.0000

Data Index: 33774 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5974. Min Act: 0.0001

Data Index: 318034 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5980. Min Act: -0.0000

Data Index: 23864 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1133158 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5878. Min Act: 0.0000

Data Index: 805164 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6041. Min Act: -0.0000

Data Index: 735053 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6224. Min Act: -0.0000

Data Index: 187520 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6003. Min Act: -0.0000

Data Index: 223009 (C4 (Web Text))

Max Activating Token Index: 240