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

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

Neuron 4570 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5837. Min Act: -0.0002

Data Index: 1399249 (Python Code)

Max Activating Token Index: 708

Text #1

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5744. Min Act: -0.0002

Data Index: 1611200 (Python Code)

Max Activating Token Index: 647

Text #2

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5099. Min Act: -0.0002

Data Index: 1653808 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5105. Min Act: -0.0002

Data Index: 1470759 (Python Code)

Max Activating Token Index: 878

Text #4

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4673. Min Act: -0.0002

Data Index: 1506421 (Python Code)

Max Activating Token Index: 746

Text #5

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4898. Min Act: -0.0002

Data Index: 1364961 (Python Code)

Max Activating Token Index: 170

Text #6

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4865. Min Act: -0.0002

Data Index: 1515839 (Python Code)

Max Activating Token Index: 264

Text #7

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4590. Min Act: -0.0002

Data Index: 1397042 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4642. Min Act: -0.0002

Data Index: 1580012 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4594. Min Act: -0.0002

Data Index: 1594692 (Python Code)

Max Activating Token Index: 569

Text #10

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4518. Min Act: -0.0002

Data Index: 1472619 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4694. Min Act: -0.0002

Data Index: 1613474 (Python Code)

Max Activating Token Index: 821

Text #12

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4122. Min Act: -0.0002

Data Index: 1449253 (Python Code)

Max Activating Token Index: 855

Text #13

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4497. Min Act: -0.0002

Data Index: 1511882 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4390. Min Act: -0.0002

Data Index: 1506019 (Python Code)

Max Activating Token Index: 921

Text #15

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4363. Min Act: -0.0002

Data Index: 1459637 (Python Code)

Max Activating Token Index: 541

Text #16

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4364. Min Act: -0.0002

Data Index: 1567867 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4718. Min Act: -0.0002

Data Index: 1417595 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4268. Min Act: -0.0002

Data Index: 1617482 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4263. Min Act: -0.0002

Data Index: 1485471 (Python Code)

Max Activating Token Index: 376