Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3411 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.1731. Min Act: -0.0001

Data Index: 1479621 (Python Code)

Max Activating Token Index: 326

Text #1

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0848. Min Act: -0.0001

Data Index: 1382186 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0494. Min Act: -0.0001

Data Index: 1554667 (Python Code)

Max Activating Token Index: 112

Text #3

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.1692. Min Act: -0.0001

Data Index: 1537526 (Python Code)

Max Activating Token Index: 593

Text #4

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0771. Min Act: -0.0001

Data Index: 1569395 (Python Code)

Max Activating Token Index: 429

Text #5

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0116. Min Act: -0.0001

Data Index: 1408129 (Python Code)

Max Activating Token Index: 142

Text #6

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.1026. Min Act: -0.0001

Data Index: 1486621 (Python Code)

Max Activating Token Index: 869

Text #7

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0745. Min Act: -0.0001

Data Index: 1612380 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9322. Min Act: -0.0001

Data Index: 1499020 (Python Code)

Max Activating Token Index: 797

Text #9

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9376. Min Act: -0.0001

Data Index: 1460757 (Python Code)

Max Activating Token Index: 1022

Text #10

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0448. Min Act: -0.0001

Data Index: 1631709 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9840. Min Act: -0.0001

Data Index: 1458554 (Python Code)

Max Activating Token Index: 780

Text #12

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9764. Min Act: -0.0001

Data Index: 1650442 (Python Code)

Max Activating Token Index: 60

Text #13

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9416. Min Act: -0.0001

Data Index: 1552890 (Python Code)

Max Activating Token Index: 108

Text #14

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9686. Min Act: -0.0001

Data Index: 1506710 (Python Code)

Max Activating Token Index: 520

Text #15

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9991. Min Act: -0.0001

Data Index: 1485690 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9332. Min Act: -0.0001

Data Index: 1489814 (Python Code)

Max Activating Token Index: 549

Text #17

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9907. Min Act: -0.0001

Data Index: 1523000 (Python Code)

Max Activating Token Index: 698

Text #18

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9593. Min Act: -0.0001

Data Index: 1368013 (Python Code)

Max Activating Token Index: 387

Text #19

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9741. Min Act: -0.0001

Data Index: 1626838 (Python Code)

Max Activating Token Index: 578