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

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

Neuron 2798 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: 0.7116. Min Range: -0.7116

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1651000 (Python Code)

Max Activating Token Index: 597

Text #1

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5913. Min Act: -0.0000

Data Index: 292780 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1558446 (Python Code)

Max Activating Token Index: 554

Text #3

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1571720 (Python Code)

Max Activating Token Index: 640

Text #4

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1539763 (Python Code)

Max Activating Token Index: 871

Text #5

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1644289 (Python Code)

Max Activating Token Index: 706

Text #6

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1458687 (Python Code)

Max Activating Token Index: 456

Text #7

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1400779 (Python Code)

Max Activating Token Index: 454

Text #8

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4491. Min Act: -0.0000

Data Index: 187766 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1389488 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.3871. Min Act: -0.0000

Data Index: 545468 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1428083 (Python Code)

Max Activating Token Index: 780

Text #12

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1424217 (Python Code)

Max Activating Token Index: 343

Text #13

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1619487 (Python Code)

Max Activating Token Index: 538

Text #14

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1633751 (Python Code)

Max Activating Token Index: 379

Text #15

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1316681 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1373003 (Python Code)

Max Activating Token Index: 730

Text #17

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1633614 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1319861 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1364610 (Python Code)

Max Activating Token Index: 296