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

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

Neuron 2055 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.1887. Min Act: -0.0001

Data Index: 1419951 (Python Code)

Max Activating Token Index: 526

Text #1

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.3679. Min Act: -0.0001

Data Index: 1411030 (Python Code)

Max Activating Token Index: 165

Text #2

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.1678. Min Act: -0.0001

Data Index: 1391484 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.1984. Min Act: -0.0001

Data Index: 1387524 (Python Code)

Max Activating Token Index: 227

Text #4

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.1522. Min Act: -0.0001

Data Index: 1629981 (Python Code)

Max Activating Token Index: 64

Text #5

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.1656. Min Act: -0.0001

Data Index: 1364332 (Python Code)

Max Activating Token Index: 73

Text #6

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.0969. Min Act: -0.0001

Data Index: 1622908 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.0491. Min Act: -0.0001

Data Index: 1616967 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.9319. Min Act: -0.0001

Data Index: 1477985 (Python Code)

Max Activating Token Index: 787

Text #9

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.8448. Min Act: -0.0001

Data Index: 1504525 (Python Code)

Max Activating Token Index: 841

Text #10

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.9563. Min Act: -0.0001

Data Index: 1590335 (Python Code)

Max Activating Token Index: 561

Text #11

Max Range: 1.3679. Min Range: -1.3679

Max Act: 1.0678. Min Act: -0.0001

Data Index: 1638855 (Python Code)

Max Activating Token Index: 268

Text #12

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.9125. Min Act: -0.0001

Data Index: 1453901 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.8748. Min Act: -0.0001

Data Index: 1361369 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.9338. Min Act: -0.0001

Data Index: 1641935 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.7360. Min Act: -0.0001

Data Index: 1376004 (Python Code)

Max Activating Token Index: 957

Text #16

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.9147. Min Act: -0.0001

Data Index: 1462644 (Python Code)

Max Activating Token Index: 936

Text #17

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.8737. Min Act: -0.0001

Data Index: 1526644 (Python Code)

Max Activating Token Index: 867

Text #18

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.7252. Min Act: -0.0001

Data Index: 1636392 (Python Code)

Max Activating Token Index: 744

Text #19

Max Range: 1.3679. Min Range: -1.3679

Max Act: 0.8542. Min Act: -0.0001

Data Index: 1571568 (Python Code)

Max Activating Token Index: 26