Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2325 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.6730. Min Act: -0.0001

Data Index: 1640685 (Python Code)

Max Activating Token Index: 859

Text #1

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.6630. Min Act: -0.0000

Data Index: 1483004 (Python Code)

Max Activating Token Index: 165

Text #2

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4706. Min Act: -0.0001

Data Index: 1378220 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4907. Min Act: -0.0001

Data Index: 1605943 (Python Code)

Max Activating Token Index: 800

Text #4

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4953. Min Act: -0.0001

Data Index: 1545385 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4827. Min Act: -0.0001

Data Index: 1477278 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.5044. Min Act: -0.0001

Data Index: 1505472 (Python Code)

Max Activating Token Index: 136

Text #7

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.5471. Min Act: -0.0001

Data Index: 1626775 (Python Code)

Max Activating Token Index: 970

Text #8

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4681. Min Act: -0.0001

Data Index: 1479060 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4426. Min Act: -0.0001

Data Index: 1565295 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4809. Min Act: -0.0001

Data Index: 1579228 (Python Code)

Max Activating Token Index: 798

Text #11

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.3840. Min Act: -0.0001

Data Index: 1525417 (Python Code)

Max Activating Token Index: 463

Text #12

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4335. Min Act: -0.0000

Data Index: 1507032 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.3912. Min Act: -0.0000

Data Index: 1465937 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.3839. Min Act: -0.0001

Data Index: 1642749 (Python Code)

Max Activating Token Index: 428

Text #15

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4017. Min Act: -0.0001

Data Index: 1592154 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.2804. Min Act: -0.0001

Data Index: 1507914 (Python Code)

Max Activating Token Index: 364

Text #17

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.2690. Min Act: -0.0001

Data Index: 1581646 (Python Code)

Max Activating Token Index: 645

Text #18

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.1975. Min Act: -0.0001

Data Index: 1514714 (Python Code)

Max Activating Token Index: 211

Text #19

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.2212. Min Act: -0.0001

Data Index: 1529472 (Python Code)

Max Activating Token Index: 585