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

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

Neuron 2679 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: 1.6168. Min Range: -1.6168

Max Act: 1.6168. Min Act: -0.0000

Data Index: 1531672 (Python Code)

Max Activating Token Index: 443

Text #1

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.4218. Min Act: -0.0001

Data Index: 1451645 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.2227. Min Act: -0.0001

Data Index: 1446695 (Python Code)

Max Activating Token Index: 553

Text #3

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0726. Min Act: -0.0001

Data Index: 1374086 (Python Code)

Max Activating Token Index: 658

Text #4

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1620019 (Python Code)

Max Activating Token Index: 948

Text #5

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.1356. Min Act: -0.0000

Data Index: 1639387 (Python Code)

Max Activating Token Index: 590

Text #6

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1616228 (Python Code)

Max Activating Token Index: 657

Text #7

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1485185 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0371. Min Act: -0.0001

Data Index: 1637495 (Python Code)

Max Activating Token Index: 790

Text #9

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1380131 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.8623. Min Act: -0.0001

Data Index: 1423116 (Python Code)

Max Activating Token Index: 672

Text #11

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0043. Min Act: -0.0001

Data Index: 1485967 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0061. Min Act: -0.0001

Data Index: 1574616 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9393. Min Act: -0.0001

Data Index: 1590114 (Python Code)

Max Activating Token Index: 336

Text #14

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0741. Min Act: -0.0001

Data Index: 1580422 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0070. Min Act: -0.0001

Data Index: 1402706 (Python Code)

Max Activating Token Index: 596

Text #16

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9141. Min Act: -0.0001

Data Index: 1490539 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9789. Min Act: -0.0001

Data Index: 1365437 (Python Code)

Max Activating Token Index: 777

Text #18

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9326. Min Act: -0.0001

Data Index: 1432464 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1652402 (Python Code)

Max Activating Token Index: 783