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

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

Neuron 4825 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: 1.0482. Min Range: -1.0482

Max Act: 1.0482. Min Act: -0.0000

Data Index: 50481 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8464. Min Act: -0.0000

Data Index: 280900 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1112474 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6552. Min Act: -0.0000

Data Index: 680081 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7771. Min Act: -0.0000

Data Index: 458777 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1619272 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1311971 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1476977 (Python Code)

Max Activating Token Index: 68

Text #8

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1180382 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1633433 (Python Code)

Max Activating Token Index: 387

Text #10

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7038. Min Act: -0.0000

Data Index: 479811 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7786. Min Act: -0.0000

Data Index: 514919 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6716. Min Act: -0.0000

Data Index: 784048 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1133686 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6668. Min Act: -0.0000

Data Index: 817692 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1490089 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6426. Min Act: -0.0000

Data Index: 173512 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1578080 (Python Code)

Max Activating Token Index: 983

Text #18

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1082337 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1557055 (Python Code)

Max Activating Token Index: 94