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

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

Neuron 3544 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1350. Min Act: -0.0000

Data Index: 803559 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1003948 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1569. Min Act: -0.0000

Data Index: 310535 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0284. Min Act: -0.0000

Data Index: 178950 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0780. Min Act: -0.0000

Data Index: 903601 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0637. Min Act: -0.0000

Data Index: 586835 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0825. Min Act: -0.0000

Data Index: 957262 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0129. Min Act: -0.0000

Data Index: 578058 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1273126 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0119. Min Act: -0.0000

Data Index: 213598 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9965. Min Act: -0.0001

Data Index: 1186461 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0445. Min Act: -0.0000

Data Index: 605688 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0498. Min Act: -0.0000

Data Index: 271133 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0405. Min Act: -0.0000

Data Index: 327837 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1286186 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1052. Min Act: -0.0000

Data Index: 128198 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0021. Min Act: -0.0001

Data Index: 67420 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1301163 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1026444 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1180767 (C4 (Web Text))

Max Activating Token Index: 925