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

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

Neuron 1248 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3329. Min Act: -0.0003

Data Index: 611611 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3201. Min Act: -0.0002

Data Index: 1265395 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3283. Min Act: -0.0002

Data Index: 996562 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3274. Min Act: -0.0003

Data Index: 1276574 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3060. Min Act: -0.0002

Data Index: 208978 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2938. Min Act: -0.0003

Data Index: 1093562 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2983. Min Act: -0.0003

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2933. Min Act: -0.0002

Data Index: 945785 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2941. Min Act: -0.0002

Data Index: 958819 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2889. Min Act: -0.0002

Data Index: 151290 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2888. Min Act: -0.0002

Data Index: 165121 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2881. Min Act: -0.0002

Data Index: 497438 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2864. Min Act: -0.0002

Data Index: 1053927 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2859. Min Act: -0.0002

Data Index: 481974 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2871. Min Act: -0.0003

Data Index: 697205 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2767. Min Act: -0.0002

Data Index: 16861 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2756. Min Act: -0.0003

Data Index: 375894 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2738. Min Act: -0.0002

Data Index: 1042346 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2709. Min Act: -0.0003

Data Index: 35186 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2694. Min Act: -0.0003

Data Index: 845228 (C4 (Web Text))

Max Activating Token Index: 809