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

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

Neuron 4749 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: 0.2573. Min Range: -0.2573

Max Act: 0.2573. Min Act: -0.0000

Data Index: 885891 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2234. Min Act: -0.0000

Data Index: 688471 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2204. Min Act: -0.0000

Data Index: 114040 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2031. Min Act: -0.0000

Data Index: 576181 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2031. Min Act: -0.0000

Data Index: 4099 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1941. Min Act: -0.0000

Data Index: 686710 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1733. Min Act: -0.0000

Data Index: 153454 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1027032 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1852. Min Act: -0.0000

Data Index: 409988 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1200583 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1583. Min Act: -0.0000

Data Index: 996677 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1141571 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1661. Min Act: -0.0000

Data Index: 151223 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1665. Min Act: -0.0000

Data Index: 601163 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1708. Min Act: -0.0000

Data Index: 979577 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1457. Min Act: -0.0000

Data Index: 823605 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1561. Min Act: -0.0000

Data Index: 477422 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1408. Min Act: -0.0000

Data Index: 974843 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1442. Min Act: -0.0000

Data Index: 63804 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1398. Min Act: -0.0000

Data Index: 978536 (C4 (Web Text))

Max Activating Token Index: 798