Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4905 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.6013. Min Act: -0.0000

Data Index: 793168 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.4714. Min Act: -0.0000

Data Index: 1536849 (Python Code)

Max Activating Token Index: 905

Text #2

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.5274. Min Act: -0.0000

Data Index: 766477 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.3006. Min Act: -0.0000

Data Index: 1368468 (Python Code)

Max Activating Token Index: 257

Text #4

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.3231. Min Act: -0.0000

Data Index: 504920 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.1908. Min Act: -0.0000

Data Index: 211470 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.2266. Min Act: -0.0000

Data Index: 486843 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1369459 (Python Code)

Max Activating Token Index: 874

Text #8

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.1772. Min Act: -0.0000

Data Index: 1307660 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1534732 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1596512 (Python Code)

Max Activating Token Index: 816

Text #11

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.2521. Min Act: -0.0000

Data Index: 312730 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.2469. Min Act: -0.0000

Data Index: 1131620 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1120799 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1576935 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.1276. Min Act: -0.0000

Data Index: 342146 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1507434 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1633470 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.0387. Min Act: -0.0000

Data Index: 719369 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.6013. Min Range: -1.6013

Max Act: 1.0958. Min Act: -0.0000

Data Index: 909066 (C4 (Web Text))

Max Activating Token Index: 414