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

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

Neuron 3844 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3730. Min Range: -2.3730

Max Act: 2.3730. Min Act: -0.0000

Data Index: 429978 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 2.3730. Min Range: -2.3730

Max Act: 2.0590. Min Act: -0.0000

Data Index: 755535 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.5159. Min Act: -0.0000

Data Index: 1176597 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.5692. Min Act: -0.0000

Data Index: 23153 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.3766. Min Act: -0.0000

Data Index: 966889 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.3888. Min Act: -0.0000

Data Index: 668738 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1312721 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.3671. Min Act: -0.0000

Data Index: 836481 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.2447. Min Act: -0.0000

Data Index: 760792 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.3343. Min Act: -0.0000

Data Index: 656803 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1122596 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.2833. Min Act: -0.0000

Data Index: 1266391 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.2317. Min Act: -0.0000

Data Index: 71669 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1344521 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.2415. Min Act: -0.0000

Data Index: 438585 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.3579. Min Act: -0.0000

Data Index: 715964 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.3079. Min Act: -0.0000

Data Index: 704823 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1180363 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1203949 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 2.3730. Min Range: -2.3730

Max Act: 1.2607. Min Act: -0.0000

Data Index: 563913 (C4 (Web Text))

Max Activating Token Index: 202