Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 448 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1556592 (Python Code)

Max Activating Token Index: 205

Text #1

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1385889 (Python Code)

Max Activating Token Index: 418

Text #2

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1395381 (Python Code)

Max Activating Token Index: 716

Text #3

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1469257 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1532296 (Python Code)

Max Activating Token Index: 405

Text #5

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1363830 (Python Code)

Max Activating Token Index: 655

Text #6

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1593874 (Python Code)

Max Activating Token Index: 527

Text #7

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1529460 (Python Code)

Max Activating Token Index: 471

Text #8

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1649553 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1634031 (Python Code)

Max Activating Token Index: 155

Text #10

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1581918 (Python Code)

Max Activating Token Index: 744

Text #11

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1423690 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1632796 (Python Code)

Max Activating Token Index: 439

Text #13

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1626162 (Python Code)

Max Activating Token Index: 720

Text #14

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1560710 (Python Code)

Max Activating Token Index: 794

Text #15

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1453394 (Python Code)

Max Activating Token Index: 51

Text #16

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1453009 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1588566 (Python Code)

Max Activating Token Index: 451

Text #18

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1537856 (Python Code)

Max Activating Token Index: 681

Text #19

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1541791 (Python Code)

Max Activating Token Index: 562