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

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

Neuron 2066 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2758. Min Range: -2.2758

Max Act: 2.2758. Min Act: -0.0000

Data Index: 830686 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 2.2758. Min Range: -2.2758

Max Act: 2.2057. Min Act: -0.0000

Data Index: 580981 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 2.2758. Min Range: -2.2758

Max Act: 2.1975. Min Act: -0.0001

Data Index: 753444 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 2.2758. Min Range: -2.2758

Max Act: 2.1782. Min Act: -0.0001

Data Index: 742003 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 2.2758. Min Range: -2.2758

Max Act: 2.1697. Min Act: -0.0001

Data Index: 307474 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.8888. Min Act: -0.0001

Data Index: 972667 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.9629. Min Act: -0.0001

Data Index: 939949 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.8735. Min Act: -0.0001

Data Index: 132112 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.8732. Min Act: -0.0001

Data Index: 985997 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.7399. Min Act: -0.0001

Data Index: 285982 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.9270. Min Act: -0.0001

Data Index: 827572 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.7210. Min Act: -0.0001

Data Index: 679466 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.6794. Min Act: -0.0000

Data Index: 570111 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.6644. Min Act: -0.0000

Data Index: 664476 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.6535. Min Act: -0.0000

Data Index: 173958 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.7153. Min Act: -0.0000

Data Index: 84704 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.7198. Min Act: -0.0001

Data Index: 1158807 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.6306. Min Act: -0.0001

Data Index: 1202074 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.7560. Min Act: -0.0001

Data Index: 64584 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 2.2758. Min Range: -2.2758

Max Act: 1.5714. Min Act: -0.0001

Data Index: 201801 (C4 (Web Text))

Max Activating Token Index: 57