Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4631 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1295342 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1248945 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1563144 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1443193 (Python Code)

Max Activating Token Index: 420

Text #4

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1485203 (Python Code)

Max Activating Token Index: 173

Text #5

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1413505 (Python Code)

Max Activating Token Index: 656

Text #6

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6041. Min Act: 0.0000

Data Index: 1574839 (Python Code)

Max Activating Token Index: 599

Text #7

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1450322 (Python Code)

Max Activating Token Index: 333

Text #8

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1502799 (Python Code)

Max Activating Token Index: 248

Text #9

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6196. Min Act: -0.0000

Data Index: 526831 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1606575 (Python Code)

Max Activating Token Index: 142

Text #11

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1450739 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.6424. Min Act: -0.0000

Data Index: 572444 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.5994. Min Act: -0.0000

Data Index: 755580 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1586896 (Python Code)

Max Activating Token Index: 983

Text #15

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1615987 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1427404 (Python Code)

Max Activating Token Index: 743

Text #17

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1545748 (Python Code)

Max Activating Token Index: 531

Text #18

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1550064 (Python Code)

Max Activating Token Index: 213

Text #19

Max Range: 0.7782. Min Range: -0.7782

Max Act: 0.5230. Min Act: -0.0000

Data Index: 169342 (C4 (Web Text))

Max Activating Token Index: 977