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

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

Neuron 2707 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2235. Min Act: -0.0000

Data Index: 215794 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1991. Min Act: -0.0000

Data Index: 937848 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1286125 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1279240 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1761. Min Act: -0.0000

Data Index: 344303 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1732. Min Act: -0.0000

Data Index: 307396 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1737. Min Act: -0.0000

Data Index: 688035 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1804. Min Act: -0.0000

Data Index: 19154 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1676. Min Act: -0.0000

Data Index: 458146 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1223086 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1665. Min Act: -0.0000

Data Index: 533889 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1735. Min Act: -0.0000

Data Index: 196433 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1743. Min Act: -0.0000

Data Index: 587376 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1549. Min Act: -0.0000

Data Index: 814923 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1635. Min Act: -0.0000

Data Index: 267421 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1624. Min Act: -0.0000

Data Index: 812772 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1710. Min Act: -0.0000

Data Index: 452917 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1474337 (Python Code)

Max Activating Token Index: 802

Text #18

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1068472 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1464. Min Act: -0.0000

Data Index: 32973 (C4 (Web Text))

Max Activating Token Index: 807