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

Dataset: The Pile

Neuron 4360 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1954223 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1855254 (The Pile)

Max Activating Token Index: 302

Text #2

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1044271 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.5067. Min Act: -0.0000

Data Index: 830848 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4874. Min Act: -0.0000

Data Index: 366433 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.5040. Min Act: -0.0000

Data Index: 59030 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1109691 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4268. Min Act: -0.0000

Data Index: 796057 (The Pile)

Max Activating Token Index: 874

Text #8

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1089109 (The Pile)

Max Activating Token Index: 560

Text #9

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4511. Min Act: -0.0000

Data Index: 412438 (The Pile)

Max Activating Token Index: 761

Text #10

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4921. Min Act: -0.0000

Data Index: 927221 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4310. Min Act: -0.0000

Data Index: 992175 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1092018 (The Pile)

Max Activating Token Index: 627

Text #13

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1819625 (The Pile)

Max Activating Token Index: 373

Text #14

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1205208 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1961297 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4417. Min Act: -0.0000

Data Index: 129279 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4427. Min Act: -0.0000

Data Index: 156951 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.4746. Min Act: -0.0000

Data Index: 42876 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 0.6004. Min Range: -0.6004

Max Act: 0.3947. Min Act: -0.0000

Data Index: 238933 (The Pile)

Max Activating Token Index: 573