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

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

Neuron 3244 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1309. Min Act: -0.0002

Data Index: 787223 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1214. Min Act: -0.0002

Data Index: 510085 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1150. Min Act: -0.0002

Data Index: 546118 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0954. Min Act: -0.0002

Data Index: 455124 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0915. Min Act: -0.0002

Data Index: 710820 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1086. Min Act: -0.0002

Data Index: 812713 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0861. Min Act: -0.0002

Data Index: 502721 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1266775 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0955. Min Act: -0.0002

Data Index: 827867 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1199270 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0982. Min Act: -0.0002

Data Index: 33916 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0845. Min Act: -0.0002

Data Index: 229293 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0986. Min Act: -0.0002

Data Index: 970502 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0950. Min Act: -0.0002

Data Index: 679070 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0795. Min Act: -0.0002

Data Index: 216655 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0812. Min Act: -0.0002

Data Index: 268241 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0891. Min Act: -0.0002

Data Index: 763858 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0837. Min Act: -0.0002

Data Index: 408368 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1351652 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1169719 (C4 (Web Text))

Max Activating Token Index: 142