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

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

Neuron 2832 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: 1.1773. Min Range: -1.1773

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1269584 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 1.1773. Min Range: -1.1773

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1025201 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 1.1773. Min Range: -1.1773

Max Act: 1.0317. Min Act: -0.0000

Data Index: 866777 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.1773. Min Range: -1.1773

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1195829 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 1.1773. Min Range: -1.1773

Max Act: 1.0649. Min Act: -0.0000

Data Index: 246238 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9889. Min Act: -0.0000

Data Index: 297242 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9856. Min Act: -0.0000

Data Index: 407774 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9640. Min Act: -0.0000

Data Index: 966524 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1250152 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9126. Min Act: -0.0000

Data Index: 697610 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9103. Min Act: -0.0000

Data Index: 288028 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1058140 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9263. Min Act: -0.0000

Data Index: 869961 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8735. Min Act: -0.0000

Data Index: 860218 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8733. Min Act: -0.0000

Data Index: 427458 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8644. Min Act: -0.0000

Data Index: 481636 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1235878 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1073249 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8527. Min Act: -0.0000

Data Index: 905335 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9023. Min Act: -0.0000

Data Index: 879106 (C4 (Web Text))

Max Activating Token Index: 975