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

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

Neuron 634 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1195022 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.8378. Min Act: -0.0000

Data Index: 925389 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.8110. Min Act: -0.0000

Data Index: 217578 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.8220. Min Act: -0.0000

Data Index: 121388 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7843. Min Act: -0.0000

Data Index: 618179 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1347540 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7458. Min Act: -0.0000

Data Index: 933896 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7476. Min Act: -0.0000

Data Index: 28204 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1042843 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6894. Min Act: -0.0000

Data Index: 963505 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7099. Min Act: -0.0000

Data Index: 684424 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6991. Min Act: -0.0000

Data Index: 282936 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6995. Min Act: -0.0000

Data Index: 94370 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1119307 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7320. Min Act: -0.0000

Data Index: 915847 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7760. Min Act: -0.0000

Data Index: 883379 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1053005 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7061. Min Act: -0.0000

Data Index: 350008 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1169186 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6416. Min Act: -0.0000

Data Index: 793262 (C4 (Web Text))

Max Activating Token Index: 1016