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

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

Neuron 3991 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.7679. Min Act: -0.0000

Data Index: 402548 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1299020 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1298181 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1092343 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1320600 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6571. Min Act: -0.0000

Data Index: 369440 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6097. Min Act: -0.0000

Data Index: 413244 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1254913 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.6066. Min Act: -0.0000

Data Index: 482363 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5855. Min Act: -0.0000

Data Index: 936608 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5980. Min Act: -0.0000

Data Index: 114434 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5868. Min Act: -0.0000

Data Index: 469430 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5534. Min Act: -0.0000

Data Index: 160005 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5483. Min Act: -0.0000

Data Index: 31504 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5427. Min Act: -0.0000

Data Index: 258013 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5719. Min Act: -0.0000

Data Index: 19458 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5853. Min Act: -0.0000

Data Index: 589622 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1323215 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1240521 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.7679. Min Range: -0.7679

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1347573 (C4 (Web Text))

Max Activating Token Index: 154