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

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

Neuron 6136 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.4733. Min Act: -0.0001

Data Index: 1616574 (Python Code)

Max Activating Token Index: 103

Text #1

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.3687. Min Act: -0.0001

Data Index: 1401784 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.3683. Min Act: -0.0001

Data Index: 1465424 (Python Code)

Max Activating Token Index: 304

Text #3

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.3306. Min Act: -0.0001

Data Index: 1446932 (Python Code)

Max Activating Token Index: 361

Text #4

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.4665. Min Act: -0.0001

Data Index: 1421627 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.2744. Min Act: -0.0001

Data Index: 1362953 (Python Code)

Max Activating Token Index: 297

Text #6

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.3564. Min Act: -0.0001

Data Index: 1644229 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.2392. Min Act: -0.0001

Data Index: 1372102 (Python Code)

Max Activating Token Index: 824

Text #8

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.1372. Min Act: -0.0000

Data Index: 1360584 (Python Code)

Max Activating Token Index: 768

Text #9

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.1365. Min Act: -0.0001

Data Index: 1389837 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.9589. Min Act: -0.0001

Data Index: 1551016 (Python Code)

Max Activating Token Index: 995

Text #11

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.9005. Min Act: -0.0001

Data Index: 1617831 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.9996. Min Act: -0.0000

Data Index: 1478361 (Python Code)

Max Activating Token Index: 771

Text #13

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.8973. Min Act: -0.0001

Data Index: 1566840 (Python Code)

Max Activating Token Index: 105

Text #14

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.8793. Min Act: -0.0001

Data Index: 1540842 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.7977. Min Act: -0.0001

Data Index: 1447940 (Python Code)

Max Activating Token Index: 816

Text #16

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.7821. Min Act: -0.0001

Data Index: 1550176 (Python Code)

Max Activating Token Index: 881

Text #17

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.7651. Min Act: -0.0001

Data Index: 1415543 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.7554. Min Act: -0.0001

Data Index: 1579783 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.7146. Min Act: -0.0001

Data Index: 1490699 (Python Code)

Max Activating Token Index: 183