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

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

Neuron 5493 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1179042 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1580003 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1642953 (Python Code)

Max Activating Token Index: 252

Text #3

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1576. Min Act: -0.0000

Data Index: 961123 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1445076 (Python Code)

Max Activating Token Index: 347

Text #5

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1472. Min Act: -0.0000

Data Index: 348604 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1220847 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1425302 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1236028 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1320. Min Act: -0.0000

Data Index: 123109 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1409941 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1527065 (Python Code)

Max Activating Token Index: 655

Text #12

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1341. Min Act: -0.0000

Data Index: 552688 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1342. Min Act: -0.0000

Data Index: 811537 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1477. Min Act: -0.0000

Data Index: 825679 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1211. Min Act: -0.0000

Data Index: 693923 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1168985 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1188. Min Act: -0.0000

Data Index: 932454 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1569595 (Python Code)

Max Activating Token Index: 793

Text #19

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1183. Min Act: -0.0000

Data Index: 782690 (C4 (Web Text))

Max Activating Token Index: 99