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

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

Neuron 2689 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0003

Data Index: 94074 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0095. Min Act: -0.0003

Data Index: 568057 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0092. Min Act: -0.0003

Data Index: 748232 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0088. Min Act: -0.0003

Data Index: 176384 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0089. Min Act: -0.0003

Data Index: 286658 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0089. Min Act: -0.0003

Data Index: 1598854 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1042879 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0078. Min Act: -0.0003

Data Index: 192747 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0081. Min Act: -0.0003

Data Index: 115604 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1044097 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0080. Min Act: -0.0004

Data Index: 893766 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0078. Min Act: -0.0003

Data Index: 689155 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0079. Min Act: -0.0003

Data Index: 415411 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0077. Min Act: -0.0003

Data Index: 71436 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0079. Min Act: -0.0003

Data Index: 699757 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1192941 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1445204 (Python Code)

Max Activating Token Index: 878

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0077. Min Act: -0.0003

Data Index: 683359 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1193274 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1647228 (Python Code)

Max Activating Token Index: 44