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

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

Neuron 1191 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.8992. Min Act: -0.0000

Data Index: 1589026 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.7883. Min Act: -0.0000

Data Index: 1368915 (Python Code)

Max Activating Token Index: 898

Text #2

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.8231. Min Act: -0.0000

Data Index: 1503909 (Python Code)

Max Activating Token Index: 636

Text #3

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.8236. Min Act: -0.0000

Data Index: 562033 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.7480. Min Act: -0.0000

Data Index: 1471046 (Python Code)

Max Activating Token Index: 651

Text #5

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.6001. Min Act: -0.0000

Data Index: 1441579 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.6774. Min Act: -0.0000

Data Index: 1648281 (Python Code)

Max Activating Token Index: 976

Text #7

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.6489. Min Act: -0.0000

Data Index: 1639254 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.6115. Min Act: -0.0000

Data Index: 1498758 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.5800. Min Act: -0.0000

Data Index: 1417877 (Python Code)

Max Activating Token Index: 433

Text #10

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.4122. Min Act: -0.0000

Data Index: 1553101 (Python Code)

Max Activating Token Index: 376

Text #11

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.4941. Min Act: -0.0000

Data Index: 1477858 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.4826. Min Act: -0.0000

Data Index: 1568513 (Python Code)

Max Activating Token Index: 411

Text #13

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.4317. Min Act: -0.0000

Data Index: 1426358 (Python Code)

Max Activating Token Index: 537

Text #14

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.4041. Min Act: -0.0000

Data Index: 1645743 (Python Code)

Max Activating Token Index: 780

Text #15

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.4116. Min Act: -0.0000

Data Index: 1498608 (Python Code)

Max Activating Token Index: 636

Text #16

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.3942. Min Act: -0.0000

Data Index: 1572252 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.3828. Min Act: -0.0000

Data Index: 1622248 (Python Code)

Max Activating Token Index: 640

Text #18

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.3803. Min Act: -0.0000

Data Index: 1618473 (Python Code)

Max Activating Token Index: 407

Text #19

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.3771. Min Act: -0.0000

Data Index: 1545425 (Python Code)

Max Activating Token Index: 463