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

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

Neuron 2778 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4976. Min Act: -0.0000

Data Index: 372830 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1268901 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1231956 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1303269 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1212734 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4571. Min Act: -0.0000

Data Index: 196514 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4456. Min Act: -0.0000

Data Index: 706427 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1317678 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4128. Min Act: -0.0000

Data Index: 508142 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3816. Min Act: -0.0000

Data Index: 524465 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3807. Min Act: -0.0000

Data Index: 475463 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1059802 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4010. Min Act: -0.0000

Data Index: 764202 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1124052 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3830. Min Act: -0.0000

Data Index: 814557 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3728. Min Act: -0.0000

Data Index: 729491 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3373. Min Act: -0.0000

Data Index: 263936 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3556. Min Act: -0.0000

Data Index: 815872 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3429. Min Act: -0.0000

Data Index: 344676 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3371. Min Act: -0.0000

Data Index: 158835 (C4 (Web Text))

Max Activating Token Index: 608