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

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

Neuron 5586 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: 1.6467. Min Range: -1.6467

Max Act: 1.6467. Min Act: -0.0000

Data Index: 1491750 (Python Code)

Max Activating Token Index: 701

Text #1

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3864. Min Act: -0.0000

Data Index: 1526679 (Python Code)

Max Activating Token Index: 61

Text #2

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1506679 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0643. Min Act: -0.0000

Data Index: 1508587 (Python Code)

Max Activating Token Index: 1016

Text #4

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1421102 (Python Code)

Max Activating Token Index: 486

Text #5

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.2019. Min Act: -0.0000

Data Index: 1558638 (Python Code)

Max Activating Token Index: 748

Text #6

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.2768. Min Act: -0.0000

Data Index: 1446677 (Python Code)

Max Activating Token Index: 771

Text #7

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1546747 (Python Code)

Max Activating Token Index: 302

Text #8

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3942. Min Act: -0.0000

Data Index: 1418964 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3334. Min Act: -0.0000

Data Index: 1410995 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1381605 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1633559 (Python Code)

Max Activating Token Index: 440

Text #12

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3613. Min Act: -0.0000

Data Index: 1470625 (Python Code)

Max Activating Token Index: 680

Text #13

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1460503 (Python Code)

Max Activating Token Index: 201

Text #14

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0866. Min Act: -0.0000

Data Index: 1451279 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.2049. Min Act: -0.0000

Data Index: 1613323 (Python Code)

Max Activating Token Index: 320

Text #16

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1656738 (Python Code)

Max Activating Token Index: 129

Text #17

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1413894 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1392472 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3268. Min Act: -0.0000

Data Index: 1516267 (Python Code)

Max Activating Token Index: 347