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

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

Neuron 728 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: 0.1248. Min Range: -0.1248

Max Act: 0.1104. Min Act: -0.0001

Data Index: 82817 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1182. Min Act: -0.0001

Data Index: 1269462 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1177. Min Act: -0.0001

Data Index: 849539 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1114. Min Act: -0.0001

Data Index: 250308 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1047. Min Act: -0.0002

Data Index: 397412 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1248. Min Act: -0.0001

Data Index: 750424 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0996. Min Act: -0.0001

Data Index: 526737 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1099046 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0961. Min Act: -0.0001

Data Index: 61983 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0934. Min Act: -0.0001

Data Index: 930896 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0918. Min Act: -0.0001

Data Index: 880252 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0896. Min Act: -0.0001

Data Index: 885324 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1140563 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1269655 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0923. Min Act: -0.0001

Data Index: 156938 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0906. Min Act: -0.0001

Data Index: 495134 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1278523 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1005886 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0871. Min Act: -0.0001

Data Index: 819262 (C4 (Web Text))

Max Activating Token Index: 898