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

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

Neuron 822 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1955. Min Range: -1.1955

Max Act: 1.1955. Min Act: -0.0000

Data Index: 680331 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 1.1955. Min Range: -1.1955

Max Act: 1.1048. Min Act: -0.0000

Data Index: 585481 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.1955. Min Range: -1.1955

Max Act: 1.0236. Min Act: -0.0001

Data Index: 302295 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9420. Min Act: -0.0000

Data Index: 192992 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1317045 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8127. Min Act: -0.0000

Data Index: 926267 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1049436 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8494. Min Act: -0.0000

Data Index: 195389 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1086887 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8080. Min Act: -0.0000

Data Index: 894362 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7293. Min Act: -0.0000

Data Index: 153126 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7429. Min Act: -0.0000

Data Index: 573729 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1298709 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7529. Min Act: -0.0000

Data Index: 544609 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7441. Min Act: -0.0000

Data Index: 224557 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7455. Min Act: -0.0000

Data Index: 968983 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.6862. Min Act: -0.0000

Data Index: 178496 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1143929 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.6870. Min Act: -0.0001

Data Index: 861955 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7048. Min Act: -0.0001

Data Index: 1558966 (Python Code)

Max Activating Token Index: 778