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

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

Neuron 1761 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.9776. Min Act: 0.0000

Data Index: 1538169 (Python Code)

Max Activating Token Index: 989

Text #1

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1604696 (Python Code)

Max Activating Token Index: 466

Text #2

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.5719. Min Act: 0.0000

Data Index: 1484288 (Python Code)

Max Activating Token Index: 529

Text #3

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.5421. Min Act: 0.0000

Data Index: 1407115 (Python Code)

Max Activating Token Index: 310

Text #4

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.5078. Min Act: 0.0000

Data Index: 1575771 (Python Code)

Max Activating Token Index: 167

Text #5

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1414641 (Python Code)

Max Activating Token Index: 560

Text #6

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4985. Min Act: 0.0000

Data Index: 1619152 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1524892 (Python Code)

Max Activating Token Index: 922

Text #8

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1394095 (Python Code)

Max Activating Token Index: 628

Text #9

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4638. Min Act: 0.0000

Data Index: 1479732 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4704. Min Act: 0.0001

Data Index: 1573595 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4346. Min Act: 0.0001

Data Index: 1487536 (Python Code)

Max Activating Token Index: 536

Text #12

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1404575 (Python Code)

Max Activating Token Index: 743

Text #13

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1620984 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1599816 (Python Code)

Max Activating Token Index: 287

Text #15

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4154. Min Act: -0.0000

Data Index: 177261 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1614400 (Python Code)

Max Activating Token Index: 351

Text #17

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.4228. Min Act: 0.0000

Data Index: 1419355 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1422475 (Python Code)

Max Activating Token Index: 869

Text #19

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1390072 (Python Code)

Max Activating Token Index: 247