Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3612 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1503372 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1580325 (Python Code)

Max Activating Token Index: 125

Text #2

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1490391 (Python Code)

Max Activating Token Index: 80

Text #3

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1413887 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1558662 (Python Code)

Max Activating Token Index: 638

Text #5

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1559062 (Python Code)

Max Activating Token Index: 356

Text #6

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1462559 (Python Code)

Max Activating Token Index: 345

Text #7

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1484789 (Python Code)

Max Activating Token Index: 177

Text #8

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1480181 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1636929 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1654439 (Python Code)

Max Activating Token Index: 64

Text #11

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1424952 (Python Code)

Max Activating Token Index: 629

Text #12

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1413359 (Python Code)

Max Activating Token Index: 988

Text #13

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1467145 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1446129 (Python Code)

Max Activating Token Index: 773

Text #15

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1427773 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1653747 (Python Code)

Max Activating Token Index: 975

Text #17

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1569384 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1482278 (Python Code)

Max Activating Token Index: 704

Text #19

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1646952 (Python Code)

Max Activating Token Index: 108