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

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

Neuron 3808 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: 0.2152. Min Range: -0.2152

Max Act: 0.2152. Min Act: -0.0000

Data Index: 87828 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1241913 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1854. Min Act: -0.0000

Data Index: 631633 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1665. Min Act: -0.0000

Data Index: 620493 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1718. Min Act: -0.0000

Data Index: 483144 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1746. Min Act: -0.0000

Data Index: 148249 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1535253 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1514. Min Act: -0.0000

Data Index: 151128 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1465. Min Act: -0.0000

Data Index: 456638 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1619022 (Python Code)

Max Activating Token Index: 518

Text #10

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1569. Min Act: -0.0000

Data Index: 819351 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1108322 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1519. Min Act: -0.0000

Data Index: 206947 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1595521 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1502. Min Act: -0.0000

Data Index: 409099 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1486. Min Act: -0.0000

Data Index: 2801 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1415. Min Act: -0.0000

Data Index: 394760 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1597181 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1541139 (Python Code)

Max Activating Token Index: 649

Text #19

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1361152 (Python Code)

Max Activating Token Index: 225