Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2171 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0649. Min Act: -0.0000

Data Index: 850564 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0155. Min Act: -0.0001

Data Index: 1117163 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.8073. Min Act: 0.0001

Data Index: 731959 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.8218. Min Act: -0.0001

Data Index: 1397694 (Python Code)

Max Activating Token Index: 308

Text #4

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6833. Min Act: -0.0000

Data Index: 451453 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1655623 (Python Code)

Max Activating Token Index: 680

Text #6

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7679. Min Act: 0.0001

Data Index: 313755 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6967. Min Act: -0.0000

Data Index: 272319 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1410066 (Python Code)

Max Activating Token Index: 925

Text #9

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6738. Min Act: -0.0001

Data Index: 259467 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1625225 (Python Code)

Max Activating Token Index: 759

Text #11

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1388067 (Python Code)

Max Activating Token Index: 960

Text #12

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1489392 (Python Code)

Max Activating Token Index: 900

Text #13

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6222. Min Act: -0.0001

Data Index: 1554305 (Python Code)

Max Activating Token Index: 550

Text #14

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6493. Min Act: -0.0000

Data Index: 860644 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6335. Min Act: -0.0000

Data Index: 399809 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1598653 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6465. Min Act: 0.0000

Data Index: 48497 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6166. Min Act: 0.0001

Data Index: 1176265 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1075512 (C4 (Web Text))

Max Activating Token Index: 706