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

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

Neuron 21 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: 0.3775. Min Range: -0.3775

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1140455 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3353. Min Act: -0.0000

Data Index: 753088 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2813. Min Act: -0.0000

Data Index: 450983 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3130. Min Act: -0.0000

Data Index: 790398 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2320. Min Act: -0.0000

Data Index: 984981 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1113039 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2001. Min Act: -0.0000

Data Index: 68416 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2109. Min Act: -0.0000

Data Index: 344842 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2007. Min Act: -0.0000

Data Index: 76937 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1302764 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1985. Min Act: -0.0000

Data Index: 972201 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1881. Min Act: -0.0000

Data Index: 155560 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1975. Min Act: -0.0000

Data Index: 161903 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1967. Min Act: -0.0000

Data Index: 650578 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1723. Min Act: -0.0000

Data Index: 383548 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1906. Min Act: -0.0000

Data Index: 145722 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1263585 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1198666 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1222053 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1626. Min Act: -0.0000

Data Index: 45606 (C4 (Web Text))

Max Activating Token Index: 937