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

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

Neuron 4683 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.5927. Min Act: -0.0000

Data Index: 1564442 (Python Code)

Max Activating Token Index: 1020

Text #1

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.1220. Min Act: -0.0000

Data Index: 1546261 (Python Code)

Max Activating Token Index: 319

Text #2

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1401030 (Python Code)

Max Activating Token Index: 649

Text #3

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0834. Min Act: -0.0000

Data Index: 1472488 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1572601 (Python Code)

Max Activating Token Index: 763

Text #5

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1387240 (Python Code)

Max Activating Token Index: 806

Text #6

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1646249 (Python Code)

Max Activating Token Index: 621

Text #7

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1396200 (Python Code)

Max Activating Token Index: 271

Text #8

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1540590 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1403739 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1517046 (Python Code)

Max Activating Token Index: 281

Text #11

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1546324 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1616804 (Python Code)

Max Activating Token Index: 500

Text #13

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1517256 (Python Code)

Max Activating Token Index: 585

Text #14

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1473290 (Python Code)

Max Activating Token Index: 737

Text #15

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.8531. Min Act: -0.0000

Data Index: 1428022 (Python Code)

Max Activating Token Index: 486

Text #16

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1616796 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1563009 (Python Code)

Max Activating Token Index: 667

Text #18

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1595832 (Python Code)

Max Activating Token Index: 100

Text #19

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1456642 (Python Code)

Max Activating Token Index: 984