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

Dataset: The Pile

Neuron 2856 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: 0.7999. Min Range: -0.7999

Max Act: 0.7999. Min Act: -0.0000

Data Index: 265261 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1320220 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7170. Min Act: -0.0000

Data Index: 996467 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7620. Min Act: -0.0000

Data Index: 813657 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1550917 (The Pile)

Max Activating Token Index: 642

Text #5

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6102. Min Act: -0.0000

Data Index: 786367 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6196. Min Act: -0.0000

Data Index: 572770 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1290534 (The Pile)

Max Activating Token Index: 547

Text #8

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1243889 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5460. Min Act: -0.0000

Data Index: 984051 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1180928 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6078. Min Act: -0.0000

Data Index: 181912 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1290607 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1693361 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5874. Min Act: -0.0000

Data Index: 647408 (The Pile)

Max Activating Token Index: 856

Text #15

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1657969 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1696067 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5738. Min Act: -0.0000

Data Index: 192537 (The Pile)

Max Activating Token Index: 83

Text #18

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5254. Min Act: -0.0000

Data Index: 240800 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1234174 (The Pile)

Max Activating Token Index: 804