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

Dataset: The Pile

Neuron 4618 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7843. Min Act: -0.0000

Data Index: 374517 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1591700 (The Pile)

Max Activating Token Index: 426

Text #2

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1371770 (The Pile)

Max Activating Token Index: 731

Text #3

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6054. Min Act: -0.0000

Data Index: 217570 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1359689 (The Pile)

Max Activating Token Index: 160

Text #5

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5304. Min Act: -0.0000

Data Index: 864077 (The Pile)

Max Activating Token Index: 590

Text #6

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6024. Min Act: -0.0000

Data Index: 423178 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5553. Min Act: -0.0000

Data Index: 935717 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1611528 (The Pile)

Max Activating Token Index: 314

Text #9

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5778. Min Act: -0.0000

Data Index: 405748 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6141. Min Act: -0.0000

Data Index: 559845 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5644. Min Act: -0.0000

Data Index: 347655 (The Pile)

Max Activating Token Index: 865

Text #12

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1561905 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.4921. Min Act: -0.0000

Data Index: 671761 (The Pile)

Max Activating Token Index: 184

Text #14

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1653800 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1881017 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1619340 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1677891 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5088. Min Act: -0.0000

Data Index: 62661 (The Pile)

Max Activating Token Index: 440

Text #19

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.4732. Min Act: -0.0000

Data Index: 939622 (The Pile)

Max Activating Token Index: 887