Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2024 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.3856. Min Act: -0.0001

Data Index: 3220 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.3595. Min Act: -0.0001

Data Index: 1342536 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.3404. Min Act: -0.0001

Data Index: 536388 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.3457. Min Act: -0.0001

Data Index: 797186 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.3432. Min Act: -0.0001

Data Index: 202218 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.3500. Min Act: -0.0001

Data Index: 110253 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.3074. Min Act: -0.0001

Data Index: 375558 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.3066. Min Act: -0.0001

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.3128. Min Act: -0.0001

Data Index: 948089 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.2928. Min Act: -0.0001

Data Index: 40079 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.2837. Min Act: -0.0001

Data Index: 1068760 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.2804. Min Act: -0.0001

Data Index: 782979 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.2995. Min Act: -0.0001

Data Index: 1121691 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.2853. Min Act: -0.0001

Data Index: 877443 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.3005. Min Act: -0.0001

Data Index: 186949 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.2830. Min Act: -0.0001

Data Index: 723212 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.2576. Min Act: -0.0001

Data Index: 86971 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.2752. Min Act: -0.0001

Data Index: 623527 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.2696. Min Act: -0.0001

Data Index: 14579 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.3856. Min Range: -0.3856

Max Act: 0.2656. Min Act: -0.0001

Data Index: 75559 (C4 (Web Text))

Max Activating Token Index: 115