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

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

Neuron 3232 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.9671. Min Act: -0.0000

Data Index: 1497324 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.7025. Min Act: -0.0000

Data Index: 1460201 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.6711. Min Act: -0.0000

Data Index: 1401808 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.3631. Min Act: -0.0001

Data Index: 1636485 (Python Code)

Max Activating Token Index: 43

Text #4

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.8350. Min Act: -0.0001

Data Index: 1607949 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 6.0464. Min Range: -6.0464

Max Act: 6.0464. Min Act: -0.0000

Data Index: 1506667 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.6747. Min Act: -0.0001

Data Index: 1392941 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.4954. Min Act: -0.0000

Data Index: 1436734 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 6.0464. Min Range: -6.0464

Max Act: 4.9736. Min Act: -0.0000

Data Index: 1529271 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.0091. Min Act: -0.0000

Data Index: 1482442 (Python Code)

Max Activating Token Index: 335

Text #10

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.3063. Min Act: -0.0000

Data Index: 1409942 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.2821. Min Act: -0.0000

Data Index: 1497009 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.2821. Min Act: -0.0000

Data Index: 1502114 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.2821. Min Act: -0.0001

Data Index: 1557636 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.2821. Min Act: -0.0000

Data Index: 1386461 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.2821. Min Act: -0.0000

Data Index: 1488998 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.2821. Min Act: -0.0000

Data Index: 1511511 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.4493. Min Act: -0.0001

Data Index: 1388231 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.2042. Min Act: -0.0000

Data Index: 1395341 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 6.0464. Min Range: -6.0464

Max Act: 5.0107. Min Act: -0.0000

Data Index: 1382172 (Python Code)

Max Activating Token Index: 865