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

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

Neuron 5083 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: 0.8801. Min Range: -0.8801

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1528770 (Python Code)

Max Activating Token Index: 118

Text #1

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1539389 (Python Code)

Max Activating Token Index: 765

Text #2

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1551047 (Python Code)

Max Activating Token Index: 988

Text #3

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1513064 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1558692 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1465398 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1536835 (Python Code)

Max Activating Token Index: 764

Text #7

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1377476 (Python Code)

Max Activating Token Index: 244

Text #8

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1629915 (Python Code)

Max Activating Token Index: 483

Text #9

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1616599 (Python Code)

Max Activating Token Index: 861

Text #10

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1491503 (Python Code)

Max Activating Token Index: 889

Text #11

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6509. Min Act: -0.0000

Data Index: 778480 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1635817 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1368035 (Python Code)

Max Activating Token Index: 957

Text #14

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1644534 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1432146 (Python Code)

Max Activating Token Index: 494

Text #16

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6156. Min Act: -0.0000

Data Index: 770826 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1560417 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1371580 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5755. Min Act: -0.0000

Data Index: 5032 (C4 (Web Text))

Max Activating Token Index: 507