Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1595 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2546. Min Act: -0.0001

Data Index: 734670 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2753. Min Act: -0.0001

Data Index: 513884 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2903. Min Act: -0.0001

Data Index: 888520 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2275. Min Act: -0.0001

Data Index: 724180 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2541. Min Act: -0.0001

Data Index: 904264 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2822. Min Act: -0.0001

Data Index: 176689 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2381. Min Act: -0.0001

Data Index: 295327 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2817. Min Act: -0.0001

Data Index: 751645 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2341. Min Act: -0.0001

Data Index: 294435 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.1960. Min Act: -0.0001

Data Index: 354602 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.1988. Min Act: -0.0001

Data Index: 871556 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2045. Min Act: -0.0001

Data Index: 424882 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.1517. Min Act: -0.0001

Data Index: 294873 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.1420. Min Act: -0.0001

Data Index: 530310 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.1737. Min Act: -0.0001

Data Index: 225449 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.1850. Min Act: -0.0001

Data Index: 1092826 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.2021. Min Act: -0.0001

Data Index: 423362 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.1629. Min Act: -0.0001

Data Index: 594119 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.1644. Min Act: -0.0001

Data Index: 452176 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.2903. Min Range: -1.2903

Max Act: 1.1331. Min Act: -0.0001

Data Index: 721557 (C4 (Web Text))

Max Activating Token Index: 225