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

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

Neuron 58 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8004. Min Range: -2.8004

Max Act: 2.8004. Min Act: -0.0000

Data Index: 1636204 (Python Code)

Max Activating Token Index: 422

Text #1

Max Range: 2.8004. Min Range: -2.8004

Max Act: 2.2772. Min Act: -0.0000

Data Index: 1426813 (Python Code)

Max Activating Token Index: 126

Text #2

Max Range: 2.8004. Min Range: -2.8004

Max Act: 2.1384. Min Act: -0.0000

Data Index: 1537136 (Python Code)

Max Activating Token Index: 298

Text #3

Max Range: 2.8004. Min Range: -2.8004

Max Act: 2.0784. Min Act: -0.0000

Data Index: 1557133 (Python Code)

Max Activating Token Index: 314

Text #4

Max Range: 2.8004. Min Range: -2.8004

Max Act: 2.0389. Min Act: -0.0000

Data Index: 1552674 (Python Code)

Max Activating Token Index: 859

Text #5

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.8905. Min Act: -0.0000

Data Index: 1550341 (Python Code)

Max Activating Token Index: 417

Text #6

Max Range: 2.8004. Min Range: -2.8004

Max Act: 2.0004. Min Act: 0.0000

Data Index: 1655118 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.7819. Min Act: 0.0000

Data Index: 1570800 (Python Code)

Max Activating Token Index: 424

Text #8

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.7471. Min Act: -0.0000

Data Index: 1651109 (Python Code)

Max Activating Token Index: 331

Text #9

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.8450. Min Act: -0.0000

Data Index: 1393118 (Python Code)

Max Activating Token Index: 422

Text #10

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.8257. Min Act: 0.0000

Data Index: 1648808 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.8035. Min Act: 0.0000

Data Index: 1572496 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.5919. Min Act: -0.0000

Data Index: 1624061 (Python Code)

Max Activating Token Index: 162

Text #13

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.5940. Min Act: -0.0000

Data Index: 1652736 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.6145. Min Act: -0.0000

Data Index: 1392734 (Python Code)

Max Activating Token Index: 675

Text #15

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.6791. Min Act: -0.0000

Data Index: 1400130 (Python Code)

Max Activating Token Index: 167

Text #16

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.5913. Min Act: -0.0000

Data Index: 1593285 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.5082. Min Act: 0.0000

Data Index: 1408211 (Python Code)

Max Activating Token Index: 307

Text #18

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.3970. Min Act: 0.0001

Data Index: 1630356 (Python Code)

Max Activating Token Index: 609

Text #19

Max Range: 2.8004. Min Range: -2.8004

Max Act: 1.5686. Min Act: 0.0000

Data Index: 1440504 (Python Code)

Max Activating Token Index: 53