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

Dataset: The Pile

Neuron 1961 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.9797. Min Act: -0.0000

Data Index: 781054 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1518260 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1626999 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8887. Min Act: -0.0000

Data Index: 99328 (The Pile)

Max Activating Token Index: 866

Text #4

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1231889 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1924146 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1322688 (The Pile)

Max Activating Token Index: 243

Text #7

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1679535 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1482433 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1647012 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1158986 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8259. Min Act: -0.0000

Data Index: 578934 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1338007 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8035. Min Act: -0.0000

Data Index: 699558 (The Pile)

Max Activating Token Index: 697

Text #14

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8324. Min Act: -0.0000

Data Index: 552788 (The Pile)

Max Activating Token Index: 293

Text #15

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1211979 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8188. Min Act: -0.0000

Data Index: 686206 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7912. Min Act: -0.0000

Data Index: 114057 (The Pile)

Max Activating Token Index: 950

Text #18

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7009. Min Act: -0.0000

Data Index: 560734 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1541092 (The Pile)

Max Activating Token Index: 336