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

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

Neuron 626 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.6695. Min Act: -0.0001

Data Index: 1376427 (Python Code)

Max Activating Token Index: 414

Text #1

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1479267 (Python Code)

Max Activating Token Index: 651

Text #2

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5706. Min Act: -0.0001

Data Index: 1391025 (Python Code)

Max Activating Token Index: 669

Text #3

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1507195 (Python Code)

Max Activating Token Index: 531

Text #4

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5344. Min Act: -0.0001

Data Index: 1508254 (Python Code)

Max Activating Token Index: 542

Text #5

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5434. Min Act: -0.0001

Data Index: 1583128 (Python Code)

Max Activating Token Index: 543

Text #6

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5028. Min Act: -0.0001

Data Index: 1501069 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4626. Min Act: -0.0001

Data Index: 1389777 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4605. Min Act: -0.0001

Data Index: 1385637 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4508. Min Act: -0.0001

Data Index: 1521632 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1443503 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4495. Min Act: -0.0001

Data Index: 1375004 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1390187 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1431942 (Python Code)

Max Activating Token Index: 424

Text #14

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4136. Min Act: -0.0001

Data Index: 1479465 (Python Code)

Max Activating Token Index: 360

Text #15

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1499626 (Python Code)

Max Activating Token Index: 365

Text #16

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1626778 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4100. Min Act: -0.0001

Data Index: 1624373 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4101. Min Act: -0.0001

Data Index: 1579029 (Python Code)

Max Activating Token Index: 89

Text #19

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1655893 (Python Code)

Max Activating Token Index: 577