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

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

Neuron 4845 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.4613. Min Act: -0.0001

Data Index: 216420 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1765. Min Act: -0.0001

Data Index: 1130173 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2643. Min Act: -0.0001

Data Index: 743156 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1766. Min Act: -0.0001

Data Index: 1324631 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2070. Min Act: -0.0001

Data Index: 522903 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.3536. Min Act: -0.0001

Data Index: 1055104 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2677. Min Act: -0.0001

Data Index: 1264878 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1980. Min Act: -0.0001

Data Index: 80780 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2133. Min Act: -0.0001

Data Index: 611685 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1445. Min Act: -0.0001

Data Index: 177859 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1333. Min Act: -0.0001

Data Index: 532987 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.0203. Min Act: -0.0001

Data Index: 459673 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1025. Min Act: -0.0001

Data Index: 960781 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1412. Min Act: -0.0001

Data Index: 1146852 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.0647. Min Act: -0.0001

Data Index: 1142892 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1479. Min Act: -0.0001

Data Index: 1401323 (Python Code)

Max Activating Token Index: 437

Text #16

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.0085. Min Act: -0.0001

Data Index: 377921 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1257. Min Act: -0.0001

Data Index: 1073910 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1355. Min Act: -0.0001

Data Index: 350147 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1215. Min Act: -0.0001

Data Index: 793122 (C4 (Web Text))

Max Activating Token Index: 733