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

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

Neuron 1177 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5759. Min Range: -3.5759

Max Act: 3.4849. Min Act: -0.0002

Data Index: 546191 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 3.5759. Min Range: -3.5759

Max Act: 3.5759. Min Act: -0.0002

Data Index: 276984 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 3.5759. Min Range: -3.5759

Max Act: 3.1944. Min Act: -0.0002

Data Index: 923176 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 3.5759. Min Range: -3.5759

Max Act: 3.1066. Min Act: -0.0002

Data Index: 1234747 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 3.5759. Min Range: -3.5759

Max Act: 3.0205. Min Act: -0.0002

Data Index: 587134 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.7623. Min Act: -0.0002

Data Index: 543841 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.7063. Min Act: -0.0002

Data Index: 985908 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.6198. Min Act: -0.0002

Data Index: 337611 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.5424. Min Act: -0.0002

Data Index: 1155186 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.5942. Min Act: -0.0002

Data Index: 318543 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.4623. Min Act: -0.0002

Data Index: 287270 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.4950. Min Act: -0.0002

Data Index: 727895 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.4619. Min Act: -0.0002

Data Index: 845017 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.3437. Min Act: -0.0002

Data Index: 972941 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.4029. Min Act: -0.0002

Data Index: 649887 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.3536. Min Act: -0.0002

Data Index: 299655 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.4706. Min Act: -0.0002

Data Index: 625072 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.2812. Min Act: -0.0002

Data Index: 780973 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 3.5759. Min Range: -3.5759

Max Act: 2.3272. Min Act: -0.0002

Data Index: 414188 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 3.5759. Min Range: -3.5759

Max Act: 1.9604. Min Act: -0.0002

Data Index: 25302 (C4 (Web Text))

Max Activating Token Index: 260