Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3857 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5389. Min Range: -2.5389

Max Act: 2.3789. Min Act: -0.0000

Data Index: 1368654 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 2.5389. Min Range: -2.5389

Max Act: 2.2841. Min Act: -0.0000

Data Index: 1599675 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 2.5389. Min Range: -2.5389

Max Act: 2.5389. Min Act: -0.0000

Data Index: 1607009 (Python Code)

Max Activating Token Index: 739

Text #3

Max Range: 2.5389. Min Range: -2.5389

Max Act: 2.4419. Min Act: -0.0001

Data Index: 1364534 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 2.5389. Min Range: -2.5389

Max Act: 2.2662. Min Act: -0.0000

Data Index: 1468523 (Python Code)

Max Activating Token Index: 727

Text #5

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.8975. Min Act: -0.0000

Data Index: 1515463 (Python Code)

Max Activating Token Index: 352

Text #6

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.8399. Min Act: -0.0000

Data Index: 1373256 (Python Code)

Max Activating Token Index: 30

Text #7

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.8957. Min Act: -0.0001

Data Index: 1613580 (Python Code)

Max Activating Token Index: 957

Text #8

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.7375. Min Act: -0.0000

Data Index: 1584991 (Python Code)

Max Activating Token Index: 682

Text #9

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.7381. Min Act: -0.0000

Data Index: 1561977 (Python Code)

Max Activating Token Index: 846

Text #10

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.7709. Min Act: -0.0000

Data Index: 1517212 (Python Code)

Max Activating Token Index: 410

Text #11

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.8023. Min Act: -0.0001

Data Index: 1448836 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.7194. Min Act: -0.0000

Data Index: 1471302 (Python Code)

Max Activating Token Index: 129

Text #13

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.6161. Min Act: -0.0000

Data Index: 1478665 (Python Code)

Max Activating Token Index: 857

Text #14

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.5368. Min Act: -0.0000

Data Index: 1455474 (Python Code)

Max Activating Token Index: 735

Text #15

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.4959. Min Act: -0.0000

Data Index: 1418515 (Python Code)

Max Activating Token Index: 86

Text #16

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.5611. Min Act: -0.0000

Data Index: 1433766 (Python Code)

Max Activating Token Index: 487

Text #17

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1615350 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.5250. Min Act: -0.0001

Data Index: 1515297 (Python Code)

Max Activating Token Index: 412

Text #19

Max Range: 2.5389. Min Range: -2.5389

Max Act: 1.5619. Min Act: -0.0001

Data Index: 1423444 (Python Code)

Max Activating Token Index: 662