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

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

Neuron 3524 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: 1.2960. Min Range: -1.2960

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1522016 (Python Code)

Max Activating Token Index: 700

Text #1

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2960. Min Act: -0.0000

Data Index: 582374 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2905. Min Act: -0.0000

Data Index: 1482578 (Python Code)

Max Activating Token Index: 600

Text #3

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.1961. Min Act: -0.0000

Data Index: 54895 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.1779. Min Act: -0.0000

Data Index: 186906 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1102560 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.0959. Min Act: -0.0000

Data Index: 226711 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.1490. Min Act: -0.0000

Data Index: 978691 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1650233 (Python Code)

Max Activating Token Index: 387

Text #9

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.1472. Min Act: -0.0000

Data Index: 828518 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.0804. Min Act: -0.0000

Data Index: 177946 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.1202. Min Act: -0.0000

Data Index: 342629 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.1189. Min Act: -0.0000

Data Index: 1577280 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1388600 (Python Code)

Max Activating Token Index: 146

Text #14

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.0999. Min Act: -0.0000

Data Index: 563658 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2074. Min Act: -0.0000

Data Index: 1630850 (Python Code)

Max Activating Token Index: 318

Text #16

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1495772 (Python Code)

Max Activating Token Index: 264

Text #17

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1572311 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.1587. Min Act: -0.0000

Data Index: 467396 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.0726. Min Act: -0.0000

Data Index: 613859 (C4 (Web Text))

Max Activating Token Index: 831