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

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

Neuron 708 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: 2.1615. Min Range: -2.1615

Max Act: 2.1615. Min Act: -0.0000

Data Index: 1654230 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.7700. Min Act: -0.0000

Data Index: 1515601 (Python Code)

Max Activating Token Index: 613

Text #2

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.6283. Min Act: -0.0000

Data Index: 1446258 (Python Code)

Max Activating Token Index: 487

Text #3

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1481536 (Python Code)

Max Activating Token Index: 717

Text #4

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.5578. Min Act: -0.0000

Data Index: 1602639 (Python Code)

Max Activating Token Index: 842

Text #5

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.5506. Min Act: -0.0000

Data Index: 1571581 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.6355. Min Act: -0.0000

Data Index: 1474677 (Python Code)

Max Activating Token Index: 584

Text #7

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.5897. Min Act: -0.0000

Data Index: 1484285 (Python Code)

Max Activating Token Index: 111

Text #8

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.5606. Min Act: -0.0000

Data Index: 1623922 (Python Code)

Max Activating Token Index: 246

Text #9

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.6926. Min Act: -0.0000

Data Index: 1527386 (Python Code)

Max Activating Token Index: 925

Text #10

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.5432. Min Act: -0.0000

Data Index: 1580205 (Python Code)

Max Activating Token Index: 492

Text #11

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.5159. Min Act: -0.0000

Data Index: 1391437 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.5445. Min Act: -0.0000

Data Index: 1428307 (Python Code)

Max Activating Token Index: 1012

Text #13

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1417965 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.4036. Min Act: -0.0000

Data Index: 1643750 (Python Code)

Max Activating Token Index: 693

Text #15

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.4722. Min Act: -0.0000

Data Index: 1537901 (Python Code)

Max Activating Token Index: 106

Text #16

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1457857 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.4452. Min Act: -0.0000

Data Index: 1472658 (Python Code)

Max Activating Token Index: 604

Text #18

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.4443. Min Act: -0.0000

Data Index: 1456166 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 2.1615. Min Range: -2.1615

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1645085 (Python Code)

Max Activating Token Index: 640