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

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

Neuron 3824 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1185. Min Act: -0.0001

Data Index: 532237 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1130. Min Act: -0.0001

Data Index: 83325 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1038. Min Act: -0.0001

Data Index: 209378 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1080. Min Act: -0.0001

Data Index: 644067 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1217922 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1090. Min Act: -0.0001

Data Index: 816671 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1351691 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1013. Min Act: -0.0001

Data Index: 509940 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0996. Min Act: -0.0001

Data Index: 790391 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0957. Min Act: -0.0001

Data Index: 68548 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1008633 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1114354 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1251252 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0970. Min Act: -0.0001

Data Index: 377041 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0946. Min Act: -0.0001

Data Index: 970016 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1342782 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1229512 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0955. Min Act: -0.0001

Data Index: 158199 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1182308 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0929. Min Act: -0.0001

Data Index: 30396 (C4 (Web Text))

Max Activating Token Index: 647