Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 361 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1554. Min Act: -0.0001

Data Index: 109695 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1432. Min Act: -0.0001

Data Index: 884316 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1090. Min Act: -0.0001

Data Index: 328059 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1132. Min Act: -0.0001

Data Index: 444805 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1023. Min Act: -0.0001

Data Index: 498358 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1021796 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1313072 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1031. Min Act: -0.0001

Data Index: 514856 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0989. Min Act: -0.0001

Data Index: 175730 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1074. Min Act: -0.0001

Data Index: 964918 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1109911 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1147293 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1000. Min Act: -0.0001

Data Index: 30253 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1002080 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1347903 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1115. Min Act: -0.0001

Data Index: 912865 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1057. Min Act: -0.0001

Data Index: 958088 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0968. Min Act: -0.0001

Data Index: 877459 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1008. Min Act: -0.0001

Data Index: 377568 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0923. Min Act: -0.0001

Data Index: 358574 (C4 (Web Text))

Max Activating Token Index: 379