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

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

Neuron 1298 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.7843. Min Act: -0.0001

Data Index: 269194 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.6424. Min Act: -0.0001

Data Index: 627152 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.7241. Min Act: -0.0001

Data Index: 277209 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.7172. Min Act: -0.0001

Data Index: 333785 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.6984. Min Act: -0.0001

Data Index: 641512 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.7199. Min Act: -0.0001

Data Index: 816666 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.5065. Min Act: -0.0001

Data Index: 110400 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.7393. Min Act: -0.0001

Data Index: 1255849 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.4778. Min Act: -0.0001

Data Index: 994715 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.4454. Min Act: -0.0001

Data Index: 681635 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1055136 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.4414. Min Act: -0.0001

Data Index: 1175516 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2923. Min Act: -0.0001

Data Index: 564982 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.1759. Min Act: -0.0001

Data Index: 1266638 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2820. Min Act: -0.0000

Data Index: 374029 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.3893. Min Act: -0.0001

Data Index: 882336 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.4669. Min Act: -0.0001

Data Index: 336048 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.3735. Min Act: -0.0000

Data Index: 583556 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2786. Min Act: -0.0000

Data Index: 926936 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.4704. Min Act: -0.0001

Data Index: 1391733 (Python Code)

Max Activating Token Index: 280