Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2474 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.6244. Min Range: -5.6244

Max Act: 5.6244. Min Act: -0.0000

Data Index: 277414 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 5.6244. Min Range: -5.6244

Max Act: 4.2460. Min Act: -0.0000

Data Index: 1458571 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 5.6244. Min Range: -5.6244

Max Act: 3.9046. Min Act: -0.0000

Data Index: 950880 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 5.6244. Min Range: -5.6244

Max Act: 3.7865. Min Act: -0.0000

Data Index: 1483819 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 5.6244. Min Range: -5.6244

Max Act: 4.2213. Min Act: -0.0000

Data Index: 1076293 (The Pile)

Max Activating Token Index: 242

Text #5

Max Range: 5.6244. Min Range: -5.6244

Max Act: 3.2962. Min Act: -0.0000

Data Index: 555696 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 5.6244. Min Range: -5.6244

Max Act: 3.2960. Min Act: -0.0000

Data Index: 308037 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 5.6244. Min Range: -5.6244

Max Act: 3.2110. Min Act: -0.0000

Data Index: 1702439 (The Pile)

Max Activating Token Index: 725

Text #8

Max Range: 5.6244. Min Range: -5.6244

Max Act: 3.1374. Min Act: -0.0000

Data Index: 1652983 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 5.6244. Min Range: -5.6244

Max Act: 3.5544. Min Act: -0.0000

Data Index: 1936342 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 5.6244. Min Range: -5.6244

Max Act: 3.1450. Min Act: -0.0000

Data Index: 1125345 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 5.6244. Min Range: -5.6244

Max Act: 3.2856. Min Act: -0.0000

Data Index: 527005 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 5.6244. Min Range: -5.6244

Max Act: 2.7509. Min Act: -0.0000

Data Index: 240640 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 5.6244. Min Range: -5.6244

Max Act: 3.3894. Min Act: -0.0000

Data Index: 1570473 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 5.6244. Min Range: -5.6244

Max Act: 2.7062. Min Act: -0.0000

Data Index: 1468398 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 5.6244. Min Range: -5.6244

Max Act: 2.8987. Min Act: -0.0000

Data Index: 1886705 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 5.6244. Min Range: -5.6244

Max Act: 2.7050. Min Act: -0.0000

Data Index: 1953753 (The Pile)

Max Activating Token Index: 282

Text #17

Max Range: 5.6244. Min Range: -5.6244

Max Act: 2.8633. Min Act: -0.0000

Data Index: 1019770 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 5.6244. Min Range: -5.6244

Max Act: 2.7968. Min Act: -0.0000

Data Index: 1228957 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 5.6244. Min Range: -5.6244

Max Act: 2.5133. Min Act: -0.0000

Data Index: 1210564 (The Pile)

Max Activating Token Index: 48