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

Dataset: The Pile

Neuron 546 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.5081. Min Act: -0.0000

Data Index: 700905 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.6810. Min Act: -0.0000

Data Index: 165951 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.6872. Min Act: -0.0000

Data Index: 233947 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.5124. Min Act: -0.0000

Data Index: 1426130 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.2367. Min Act: -0.0000

Data Index: 1846997 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.2679. Min Act: -0.0000

Data Index: 1574340 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3828. Min Act: -0.0000

Data Index: 371395 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3658. Min Act: -0.0000

Data Index: 125324 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.0460. Min Act: -0.0000

Data Index: 1949813 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.0367. Min Act: -0.0000

Data Index: 1491046 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.1689. Min Act: -0.0000

Data Index: 119906 (The Pile)

Max Activating Token Index: 672

Text #11

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.5923. Min Act: -0.0000

Data Index: 1119332 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.2484. Min Act: -0.0000

Data Index: 202371 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.2126. Min Act: -0.0000

Data Index: 316069 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.4200. Min Act: -0.0000

Data Index: 1151913 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 3.6872. Min Range: -3.6872

Max Act: 2.8822. Min Act: -0.0000

Data Index: 1091389 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 3.6872. Min Range: -3.6872

Max Act: 2.8405. Min Act: -0.0000

Data Index: 1635981 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 3.6872. Min Range: -3.6872

Max Act: 2.9772. Min Act: -0.0000

Data Index: 985659 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.1536. Min Act: -0.0000

Data Index: 28879 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 3.6872. Min Range: -3.6872

Max Act: 2.8271. Min Act: -0.0000

Data Index: 505367 (The Pile)

Max Activating Token Index: 971