Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 746 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2094. Min Act: -0.0003

Data Index: 327318 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2085. Min Act: -0.0003

Data Index: 315636 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2090. Min Act: -0.0003

Data Index: 296543 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1968. Min Act: -0.0003

Data Index: 122666 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1913. Min Act: -0.0003

Data Index: 337970 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1976. Min Act: -0.0003

Data Index: 129762 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2035. Min Act: -0.0003

Data Index: 578059 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1921. Min Act: -0.0003

Data Index: 609651 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1920. Min Act: -0.0003

Data Index: 77322 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1834. Min Act: -0.0003

Data Index: 1047959 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1775. Min Act: -0.0003

Data Index: 1253672 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1768. Min Act: -0.0003

Data Index: 314150 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1680. Min Act: -0.0003

Data Index: 391347 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1662. Min Act: -0.0003

Data Index: 1011944 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1716. Min Act: -0.0003

Data Index: 1050296 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1794. Min Act: -0.0003

Data Index: 701041 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1600. Min Act: -0.0003

Data Index: 34348 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1694. Min Act: -0.0003

Data Index: 584138 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1535. Min Act: -0.0003

Data Index: 1029435 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1747. Min Act: -0.0003

Data Index: 563257 (C4 (Web Text))

Max Activating Token Index: 908