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

Dataset: The Pile

Neuron 2505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.6688. Min Act: -0.0000

Data Index: 409472 (The Pile)

Max Activating Token Index: 981

Text #1

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1404432 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5156. Min Act: -0.0000

Data Index: 744281 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5127. Min Act: -0.0000

Data Index: 90967 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1311625 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1861936 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1437878 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4570. Min Act: -0.0000

Data Index: 195469 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1546775 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1250340 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1076023 (The Pile)

Max Activating Token Index: 830

Text #11

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1932160 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4232. Min Act: -0.0000

Data Index: 858542 (The Pile)

Max Activating Token Index: 373

Text #13

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1454085 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4159. Min Act: -0.0000

Data Index: 383248 (The Pile)

Max Activating Token Index: 143

Text #15

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1473996 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4064. Min Act: -0.0000

Data Index: 581754 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1777967 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4013. Min Act: -0.0000

Data Index: 310316 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1552900 (The Pile)

Max Activating Token Index: 532