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

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

Neuron 3910 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0424. Min Range: -7.0424

Max Act: 7.0424. Min Act: -0.0000

Data Index: 1431456 (Python Code)

Max Activating Token Index: 790

Text #1

Max Range: 7.0424. Min Range: -7.0424

Max Act: 6.7240. Min Act: -0.0000

Data Index: 1509064 (Python Code)

Max Activating Token Index: 485

Text #2

Max Range: 7.0424. Min Range: -7.0424

Max Act: 6.3642. Min Act: -0.0000

Data Index: 1585970 (Python Code)

Max Activating Token Index: 627

Text #3

Max Range: 7.0424. Min Range: -7.0424

Max Act: 6.5460. Min Act: -0.0000

Data Index: 1598053 (Python Code)

Max Activating Token Index: 758

Text #4

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.7499. Min Act: -0.0000

Data Index: 1571467 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.7249. Min Act: -0.0000

Data Index: 1631784 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.7311. Min Act: -0.0000

Data Index: 1380227 (Python Code)

Max Activating Token Index: 752

Text #7

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.5141. Min Act: -0.0000

Data Index: 1398467 (Python Code)

Max Activating Token Index: 614

Text #8

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.2973. Min Act: -0.0000

Data Index: 1442922 (Python Code)

Max Activating Token Index: 908

Text #9

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.4055. Min Act: -0.0000

Data Index: 1543647 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.1918. Min Act: -0.0000

Data Index: 1654464 (Python Code)

Max Activating Token Index: 928

Text #11

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.1991. Min Act: -0.0000

Data Index: 1361197 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.3408. Min Act: -0.0000

Data Index: 1572711 (Python Code)

Max Activating Token Index: 1015

Text #13

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.3830. Min Act: -0.0000

Data Index: 1434955 (Python Code)

Max Activating Token Index: 954

Text #14

Max Range: 7.0424. Min Range: -7.0424

Max Act: 5.3775. Min Act: -0.0000

Data Index: 1416660 (Python Code)

Max Activating Token Index: 91

Text #15

Max Range: 7.0424. Min Range: -7.0424

Max Act: 4.6715. Min Act: -0.0000

Data Index: 1557097 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 7.0424. Min Range: -7.0424

Max Act: 4.9785. Min Act: -0.0000

Data Index: 1482278 (Python Code)

Max Activating Token Index: 505

Text #17

Max Range: 7.0424. Min Range: -7.0424

Max Act: 4.7695. Min Act: -0.0000

Data Index: 1474567 (Python Code)

Max Activating Token Index: 75

Text #18

Max Range: 7.0424. Min Range: -7.0424

Max Act: 4.5272. Min Act: -0.0000

Data Index: 1442801 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 7.0424. Min Range: -7.0424

Max Act: 4.6532. Min Act: -0.0000

Data Index: 1612569 (Python Code)

Max Activating Token Index: 852