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

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

Neuron 1156 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.7245. Min Act: -0.0000

Data Index: 655499 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.6931. Min Act: -0.0000

Data Index: 660193 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.2253. Min Act: -0.0000

Data Index: 267375 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.3299. Min Act: -0.0000

Data Index: 849063 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.1766. Min Act: -0.0000

Data Index: 935048 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.1599. Min Act: -0.0000

Data Index: 1014482 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.2306. Min Act: -0.0000

Data Index: 462332 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.3285. Min Act: -0.0000

Data Index: 508450 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.2234. Min Act: -0.0000

Data Index: 16566 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.1809. Min Act: -0.0000

Data Index: 490744 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.1639. Min Act: -0.0000

Data Index: 1062656 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.1630. Min Act: -0.0000

Data Index: 97636 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 2.7245. Min Range: -2.7245

Max Act: 1.9086. Min Act: -0.0000

Data Index: 1213831 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 2.7245. Min Range: -2.7245

Max Act: 1.8659. Min Act: -0.0000

Data Index: 1308449 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 2.7245. Min Range: -2.7245

Max Act: 2.1388. Min Act: -0.0000

Data Index: 37501 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 2.7245. Min Range: -2.7245

Max Act: 1.9737. Min Act: -0.0000

Data Index: 1195491 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 2.7245. Min Range: -2.7245

Max Act: 1.8713. Min Act: -0.0000

Data Index: 1038609 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 2.7245. Min Range: -2.7245

Max Act: 1.9650. Min Act: -0.0000

Data Index: 226426 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 2.7245. Min Range: -2.7245

Max Act: 1.8519. Min Act: -0.0000

Data Index: 941651 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 2.7245. Min Range: -2.7245

Max Act: 1.7148. Min Act: -0.0000

Data Index: 332360 (C4 (Web Text))

Max Activating Token Index: 860