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

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

Neuron 3242 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3875. Min Range: -4.3875

Max Act: 4.2606. Min Act: -0.0000

Data Index: 533473 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 4.3875. Min Range: -4.3875

Max Act: 4.3875. Min Act: -0.0000

Data Index: 839438 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.8417. Min Act: -0.0000

Data Index: 897359 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 4.3875. Min Range: -4.3875

Max Act: 4.1203. Min Act: -0.0000

Data Index: 815052 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 4.3875. Min Range: -4.3875

Max Act: 4.1005. Min Act: -0.0000

Data Index: 833972 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.7415. Min Act: -0.0000

Data Index: 928691 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.4854. Min Act: -0.0000

Data Index: 1142201 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.7895. Min Act: -0.0000

Data Index: 586232 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.7343. Min Act: -0.0000

Data Index: 892733 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.7070. Min Act: -0.0000

Data Index: 1358144 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.6665. Min Act: -0.0000

Data Index: 703698 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.4531. Min Act: -0.0000

Data Index: 1116758 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.3668. Min Act: -0.0000

Data Index: 1257553 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.1621. Min Act: -0.0000

Data Index: 1324220 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.4260. Min Act: -0.0000

Data Index: 713726 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.0884. Min Act: -0.0000

Data Index: 285242 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 4.3875. Min Range: -4.3875

Max Act: 2.8671. Min Act: -0.0000

Data Index: 124311 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.1061. Min Act: -0.0000

Data Index: 428395 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.0240. Min Act: -0.0000

Data Index: 157140 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 4.3875. Min Range: -4.3875

Max Act: 3.1898. Min Act: -0.0000

Data Index: 1020990 (C4 (Web Text))

Max Activating Token Index: 761