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

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

Neuron 4017 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1720. Min Range: -1.1720

Max Act: 1.1720. Min Act: -0.0001

Data Index: 1219484 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 1.1720. Min Range: -1.1720

Max Act: 1.1073. Min Act: -0.0001

Data Index: 1638858 (Python Code)

Max Activating Token Index: 876

Text #2

Max Range: 1.1720. Min Range: -1.1720

Max Act: 1.0771. Min Act: -0.0001

Data Index: 1107414 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.9736. Min Act: -0.0001

Data Index: 1417720 (Python Code)

Max Activating Token Index: 293

Text #4

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8512. Min Act: -0.0001

Data Index: 1475124 (Python Code)

Max Activating Token Index: 675

Text #5

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.9711. Min Act: -0.0001

Data Index: 1509815 (Python Code)

Max Activating Token Index: 995

Text #6

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.9554. Min Act: -0.0001

Data Index: 883640 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8969. Min Act: -0.0001

Data Index: 1645280 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.9043. Min Act: -0.0001

Data Index: 1490058 (Python Code)

Max Activating Token Index: 797

Text #9

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8308. Min Act: -0.0001

Data Index: 881596 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.9600. Min Act: -0.0001

Data Index: 1488491 (Python Code)

Max Activating Token Index: 862

Text #11

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8723. Min Act: -0.0001

Data Index: 1524055 (Python Code)

Max Activating Token Index: 663

Text #12

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.9422. Min Act: -0.0001

Data Index: 1521711 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.9286. Min Act: -0.0001

Data Index: 1533064 (Python Code)

Max Activating Token Index: 343

Text #14

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.9491. Min Act: -0.0001

Data Index: 1436020 (Python Code)

Max Activating Token Index: 650

Text #15

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8369. Min Act: -0.0001

Data Index: 1528030 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.9131. Min Act: -0.0001

Data Index: 621826 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8481. Min Act: -0.0001

Data Index: 1533958 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8781. Min Act: -0.0001

Data Index: 1488205 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 1.1720. Min Range: -1.1720

Max Act: 0.8470. Min Act: -0.0001

Data Index: 1136190 (C4 (Web Text))

Max Activating Token Index: 206