Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 329 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3901. Min Act: -0.0001

Data Index: 319985 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1333651 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1124440 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1543342 (Python Code)

Max Activating Token Index: 284

Text #4

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2306. Min Act: -0.0001

Data Index: 1603167 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.0779. Min Act: -0.0001

Data Index: 961741 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3175. Min Act: -0.0000

Data Index: 324277 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1414609 (Python Code)

Max Activating Token Index: 727

Text #8

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1555658 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1977. Min Act: -0.0000

Data Index: 115639 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1853. Min Act: -0.0001

Data Index: 1648517 (Python Code)

Max Activating Token Index: 101

Text #11

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1594220 (Python Code)

Max Activating Token Index: 635

Text #12

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1488998 (Python Code)

Max Activating Token Index: 198

Text #13

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1552227 (Python Code)

Max Activating Token Index: 248

Text #14

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1164610 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1729. Min Act: -0.0001

Data Index: 1146109 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1613625 (Python Code)

Max Activating Token Index: 521

Text #17

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1579831 (Python Code)

Max Activating Token Index: 387

Text #18

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1398925 (Python Code)

Max Activating Token Index: 749

Text #19

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1576881 (Python Code)

Max Activating Token Index: 617