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

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

Neuron 3409 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1625424 (Python Code)

Max Activating Token Index: 813

Text #1

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1492298 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1204439 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1388358 (Python Code)

Max Activating Token Index: 263

Text #4

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1115397 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1646746 (Python Code)

Max Activating Token Index: 970

Text #6

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3790. Min Act: 0.0000

Data Index: 1531059 (Python Code)

Max Activating Token Index: 742

Text #7

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1239985 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3594. Min Act: -0.0000

Data Index: 829969 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1087154 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1502593 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1427715 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1487693 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1035416 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1407802 (Python Code)

Max Activating Token Index: 826

Text #15

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1576940 (Python Code)

Max Activating Token Index: 188

Text #16

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3422. Min Act: -0.0000

Data Index: 932393 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1367825 (Python Code)

Max Activating Token Index: 798

Text #18

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1535777 (Python Code)

Max Activating Token Index: 871

Text #19

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.3319. Min Act: -0.0000

Data Index: 392163 (C4 (Web Text))

Max Activating Token Index: 842