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

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

Neuron 800 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1063. Min Act: -0.0000

Data Index: 33646 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0936. Min Act: -0.0000

Data Index: 374574 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1018764 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0986. Min Act: -0.0000

Data Index: 746192 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1114837 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0786. Min Act: -0.0000

Data Index: 261668 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1063503 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1268138 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1287195 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0753. Min Act: -0.0000

Data Index: 560696 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0781. Min Act: -0.0000

Data Index: 945161 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0751. Min Act: -0.0000

Data Index: 709583 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0723. Min Act: -0.0000

Data Index: 890524 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1500782 (Python Code)

Max Activating Token Index: 576

Text #14

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0764. Min Act: -0.0000

Data Index: 1422398 (Python Code)

Max Activating Token Index: 942

Text #15

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0713. Min Act: -0.0000

Data Index: 82730 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1168827 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0706. Min Act: -0.0000

Data Index: 882398 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0694. Min Act: -0.0000

Data Index: 965026 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1135723 (C4 (Web Text))

Max Activating Token Index: 338