Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2518 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1242782 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0873. Min Act: -0.0001

Data Index: 116971 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1096140 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0826. Min Act: -0.0002

Data Index: 222275 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0831. Min Act: -0.0001

Data Index: 55156 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0922. Min Act: -0.0001

Data Index: 246155 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0804. Min Act: -0.0001

Data Index: 287520 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0825. Min Act: -0.0001

Data Index: 553778 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1047826 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1259788 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0817. Min Act: -0.0001

Data Index: 460222 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0820. Min Act: -0.0002

Data Index: 318324 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1224229 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0813. Min Act: -0.0001

Data Index: 322554 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0784. Min Act: -0.0002

Data Index: 150346 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0755. Min Act: -0.0002

Data Index: 511342 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0783. Min Act: -0.0002

Data Index: 18269 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0802. Min Act: -0.0002

Data Index: 131066 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0777. Min Act: -0.0002

Data Index: 949837 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1228673 (C4 (Web Text))

Max Activating Token Index: 756