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

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

Neuron 3835 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0857. Min Range: -6.0857

Max Act: 6.0857. Min Act: -0.0000

Data Index: 1269427 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 6.0857. Min Range: -6.0857

Max Act: 2.6478. Min Act: -0.0000

Data Index: 550824 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 6.0857. Min Range: -6.0857

Max Act: 3.5774. Min Act: -0.0000

Data Index: 474089 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.8601. Min Act: -0.0000

Data Index: 140442 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.2026. Min Act: -0.0000

Data Index: 944050 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1064914 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1103386 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1189611 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.7580. Min Act: -0.0000

Data Index: 626429 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.6825. Min Act: -0.0000

Data Index: 753623 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1348734 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1050851 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1254404 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.2824. Min Act: -0.0000

Data Index: 595278 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1073316 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.5860. Min Act: -0.0000

Data Index: 115446 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.6017. Min Act: -0.0000

Data Index: 615655 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.7398. Min Act: -0.0000

Data Index: 72483 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.5370. Min Act: -0.0000

Data Index: 493330 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 6.0857. Min Range: -6.0857

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1082783 (C4 (Web Text))

Max Activating Token Index: 380