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

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

Neuron 3823 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: 3.2802. Min Range: -3.2802

Max Act: 3.2522. Min Act: -0.0000

Data Index: 79569 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.8488. Min Act: -0.0000

Data Index: 19468 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.2802. Min Act: -0.0000

Data Index: 599060 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.1807. Min Act: -0.0000

Data Index: 630520 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.9957. Min Act: -0.0000

Data Index: 977579 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.8665. Min Act: -0.0000

Data Index: 269366 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.9713. Min Act: -0.0000

Data Index: 1307272 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.8486. Min Act: -0.0000

Data Index: 767419 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.8417. Min Act: -0.0000

Data Index: 98901 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.9260. Min Act: -0.0000

Data Index: 1296877 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.8910. Min Act: -0.0000

Data Index: 426152 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.8770. Min Act: -0.0000

Data Index: 1027089 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.6922. Min Act: -0.0000

Data Index: 958332 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.5473. Min Act: -0.0000

Data Index: 1257220 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.5462. Min Act: -0.0000

Data Index: 893935 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.7173. Min Act: -0.0000

Data Index: 1109267 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.4290. Min Act: -0.0000

Data Index: 527571 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.4215. Min Act: -0.0000

Data Index: 1052729 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.4123. Min Act: -0.0000

Data Index: 1153617 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.5402. Min Act: -0.0000

Data Index: 981629 (C4 (Web Text))

Max Activating Token Index: 286