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

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

Neuron 5309 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.7606. Min Act: -0.0000

Data Index: 1622166 (Python Code)

Max Activating Token Index: 394

Text #1

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.8890. Min Act: -0.0000

Data Index: 1435295 (Python Code)

Max Activating Token Index: 391

Text #2

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.5681. Min Act: -0.0000

Data Index: 1498034 (Python Code)

Max Activating Token Index: 612

Text #3

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.4727. Min Act: -0.0000

Data Index: 1470904 (Python Code)

Max Activating Token Index: 98

Text #4

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.9635. Min Act: -0.0000

Data Index: 1371391 (Python Code)

Max Activating Token Index: 234

Text #5

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.4273. Min Act: -0.0000

Data Index: 1381140 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.5292. Min Act: -0.0000

Data Index: 1418126 (Python Code)

Max Activating Token Index: 544

Text #7

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.2822. Min Act: -0.0000

Data Index: 1540452 (Python Code)

Max Activating Token Index: 366

Text #8

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.3768. Min Act: -0.0000

Data Index: 1646659 (Python Code)

Max Activating Token Index: 417

Text #9

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.3728. Min Act: -0.0000

Data Index: 1412043 (Python Code)

Max Activating Token Index: 203

Text #10

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.0387. Min Act: -0.0000

Data Index: 1615492 (Python Code)

Max Activating Token Index: 718

Text #11

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.2529. Min Act: -0.0000

Data Index: 1386511 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.2566. Min Act: -0.0000

Data Index: 1449612 (Python Code)

Max Activating Token Index: 948

Text #13

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.3293. Min Act: -0.0000

Data Index: 1404886 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.3204. Min Act: -0.0000

Data Index: 1461373 (Python Code)

Max Activating Token Index: 618

Text #15

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.2032. Min Act: -0.0000

Data Index: 1551865 (Python Code)

Max Activating Token Index: 898

Text #16

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.1937. Min Act: -0.0000

Data Index: 1380121 (Python Code)

Max Activating Token Index: 485

Text #17

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.1686. Min Act: -0.0000

Data Index: 1608824 (Python Code)

Max Activating Token Index: 464

Text #18

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.2820. Min Act: -0.0000

Data Index: 1537280 (Python Code)

Max Activating Token Index: 500

Text #19

Max Range: 2.9635. Min Range: -2.9635

Max Act: 2.2882. Min Act: -0.0000

Data Index: 1399821 (Python Code)

Max Activating Token Index: 764