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

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

Neuron 2943 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.4030. Min Act: -0.0000

Data Index: 1275644 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.3560. Min Act: -0.0000

Data Index: 964155 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.3803. Min Act: -0.0000

Data Index: 106470 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1093535 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.2604. Min Act: -0.0000

Data Index: 934827 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.2496. Min Act: -0.0000

Data Index: 1419660 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.1780. Min Act: -0.0000

Data Index: 746711 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.1300. Min Act: -0.0000

Data Index: 725030 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1226076 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1633903 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 1.4030. Min Range: -1.4030

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1374073 (Python Code)

Max Activating Token Index: 277

Text #11

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.0856. Min Act: -0.0000

Data Index: 877889 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 1.4030. Min Range: -1.4030

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1365207 (Python Code)

Max Activating Token Index: 654

Text #13

Max Range: 1.4030. Min Range: -1.4030

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1463876 (Python Code)

Max Activating Token Index: 1001

Text #14

Max Range: 1.4030. Min Range: -1.4030

Max Act: 0.9874. Min Act: -0.0001

Data Index: 1616520 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 1.4030. Min Range: -1.4030

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1246675 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 1.4030. Min Range: -1.4030

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1481249 (Python Code)

Max Activating Token Index: 287

Text #17

Max Range: 1.4030. Min Range: -1.4030

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1518484 (Python Code)

Max Activating Token Index: 81

Text #18

Max Range: 1.4030. Min Range: -1.4030

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1501053 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 1.4030. Min Range: -1.4030

Max Act: 0.9722. Min Act: -0.0000

Data Index: 426702 (C4 (Web Text))

Max Activating Token Index: 432