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

Dataset: The Pile

Neuron 2037 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1174043 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1653856 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1358328 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1248691 (The Pile)

Max Activating Token Index: 918

Text #4

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6478. Min Act: -0.0000

Data Index: 603668 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1970376 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5378. Min Act: -0.0000

Data Index: 174143 (The Pile)

Max Activating Token Index: 12

Text #7

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5549. Min Act: -0.0000

Data Index: 700068 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5946. Min Act: -0.0000

Data Index: 109972 (The Pile)

Max Activating Token Index: 189

Text #9

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1668632 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1504376 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5501. Min Act: -0.0000

Data Index: 362301 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1941390 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5807. Min Act: -0.0000

Data Index: 677574 (The Pile)

Max Activating Token Index: 577

Text #14

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1931313 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5952. Min Act: -0.0000

Data Index: 34962 (The Pile)

Max Activating Token Index: 865

Text #16

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5588. Min Act: -0.0000

Data Index: 752472 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1942820 (The Pile)

Max Activating Token Index: 70

Text #18

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5264. Min Act: -0.0000

Data Index: 399412 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5224. Min Act: -0.0000

Data Index: 241923 (The Pile)

Max Activating Token Index: 762