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

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

Neuron 3901 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: 3.0078. Min Range: -3.0078

Max Act: 3.0078. Min Act: -0.0000

Data Index: 872188 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9535. Min Act: -0.0000

Data Index: 57625 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.6116. Min Act: -0.0001

Data Index: 374244 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.0587. Min Act: -0.0000

Data Index: 516591 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.9975. Min Act: -0.0001

Data Index: 1315965 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.8554. Min Act: -0.0000

Data Index: 147600 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.7304. Min Act: -0.0000

Data Index: 799061 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.6200. Min Act: -0.0001

Data Index: 177383 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.5966. Min Act: -0.0000

Data Index: 205777 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.5611. Min Act: -0.0000

Data Index: 889848 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.5717. Min Act: -0.0000

Data Index: 1147646 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.4952. Min Act: -0.0000

Data Index: 1253759 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.4538. Min Act: -0.0001

Data Index: 527742 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.4584. Min Act: -0.0001

Data Index: 1030729 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.5344. Min Act: -0.0000

Data Index: 412653 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.4043. Min Act: -0.0000

Data Index: 608837 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.4481. Min Act: -0.0000

Data Index: 1011889 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.4017. Min Act: -0.0000

Data Index: 310657 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.4243. Min Act: -0.0000

Data Index: 751520 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 3.0078. Min Range: -3.0078

Max Act: 1.3829. Min Act: -0.0001

Data Index: 258113 (C4 (Web Text))

Max Activating Token Index: 642