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

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

Neuron 2896 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: 0.1758. Min Range: -0.1758

Max Act: 0.1758. Min Act: -0.0002

Data Index: 1050335 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1439. Min Act: -0.0002

Data Index: 1056618 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1200. Min Act: -0.0001

Data Index: 312301 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1324. Min Act: -0.0002

Data Index: 66149 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1210. Min Act: -0.0002

Data Index: 945005 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1182. Min Act: -0.0002

Data Index: 825898 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1126. Min Act: -0.0002

Data Index: 813157 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1103. Min Act: -0.0002

Data Index: 688572 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1063. Min Act: -0.0002

Data Index: 908948 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1067145 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.0877. Min Act: -0.0002

Data Index: 132747 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1093. Min Act: -0.0001

Data Index: 23744 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1011. Min Act: -0.0001

Data Index: 475613 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1000. Min Act: -0.0002

Data Index: 72241 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.0990. Min Act: -0.0002

Data Index: 218101 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.0946. Min Act: -0.0002

Data Index: 373475 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.0942. Min Act: -0.0002

Data Index: 591175 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1332890 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1289128 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.0937. Min Act: -0.0002

Data Index: 909893 (C4 (Web Text))

Max Activating Token Index: 726