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

Dataset: The Pile

Neuron 3140 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1330318 (The Pile)

Max Activating Token Index: 713

Text #1

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1412208 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1123447 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1370124 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1501879 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1453580 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1208787 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4044. Min Act: -0.0000

Data Index: 813061 (The Pile)

Max Activating Token Index: 168

Text #8

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4279. Min Act: -0.0000

Data Index: 143110 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3832. Min Act: -0.0000

Data Index: 961285 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3799. Min Act: -0.0000

Data Index: 567280 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4120. Min Act: -0.0000

Data Index: 161338 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1719767 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1877437 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1903553 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3747. Min Act: -0.0000

Data Index: 151486 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1215611 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3288. Min Act: -0.0000

Data Index: 677569 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3380. Min Act: -0.0000

Data Index: 126617 (The Pile)

Max Activating Token Index: 626

Text #19

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3776. Min Act: -0.0000

Data Index: 972867 (The Pile)

Max Activating Token Index: 31