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

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

Neuron 1286 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1267. Min Act: -0.0001

Data Index: 351893 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0974. Min Act: -0.0001

Data Index: 810690 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1093. Min Act: -0.0001

Data Index: 134012 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0966. Min Act: -0.0002

Data Index: 148903 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0953. Min Act: -0.0001

Data Index: 705710 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0940. Min Act: -0.0001

Data Index: 15532 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0970. Min Act: -0.0002

Data Index: 224235 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0944. Min Act: -0.0001

Data Index: 500561 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1142579 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1001. Min Act: -0.0002

Data Index: 372386 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0921. Min Act: -0.0001

Data Index: 300237 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0997. Min Act: -0.0002

Data Index: 891347 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0921. Min Act: -0.0001

Data Index: 848891 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0910. Min Act: -0.0001

Data Index: 39090 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0869. Min Act: -0.0002

Data Index: 35561 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0895. Min Act: -0.0002

Data Index: 709930 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1358338 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0856. Min Act: -0.0002

Data Index: 403829 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0887. Min Act: -0.0001

Data Index: 66937 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0879. Min Act: -0.0002

Data Index: 570647 (C4 (Web Text))

Max Activating Token Index: 570