Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3255 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1092226 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0845. Min Act: -0.0001

Data Index: 508371 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0717. Min Act: -0.0001

Data Index: 153155 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0713. Min Act: -0.0001

Data Index: 606708 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0739. Min Act: -0.0001

Data Index: 661311 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1191990 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0700. Min Act: -0.0001

Data Index: 507130 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1102732 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0715. Min Act: -0.0001

Data Index: 457062 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0706. Min Act: -0.0001

Data Index: 857811 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1314174 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1117866 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1474732 (Python Code)

Max Activating Token Index: 948

Text #13

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0647. Min Act: -0.0001

Data Index: 216426 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0675. Min Act: -0.0001

Data Index: 702112 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1227602 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0630. Min Act: -0.0001

Data Index: 112220 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0643. Min Act: -0.0001

Data Index: 60673 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0682. Min Act: -0.0001

Data Index: 259467 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0679. Min Act: -0.0001

Data Index: 722208 (C4 (Web Text))

Max Activating Token Index: 484