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

Dataset: The Pile

Neuron 2354 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: 0.7027. Min Range: -0.7027

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1740084 (The Pile)

Max Activating Token Index: 600

Text #1

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.6063. Min Act: -0.0000

Data Index: 138438 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5966. Min Act: -0.0000

Data Index: 175104 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5867. Min Act: -0.0000

Data Index: 396142 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5699. Min Act: -0.0000

Data Index: 91231 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1855226 (The Pile)

Max Activating Token Index: 908

Text #6

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5174. Min Act: -0.0000

Data Index: 705635 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5979. Min Act: -0.0000

Data Index: 674800 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4844. Min Act: -0.0000

Data Index: 588622 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5221. Min Act: -0.0000

Data Index: 809841 (The Pile)

Max Activating Token Index: 469

Text #10

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1093936 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1727322 (The Pile)

Max Activating Token Index: 355

Text #12

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4984. Min Act: -0.0000

Data Index: 873987 (The Pile)

Max Activating Token Index: 631

Text #13

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1475847 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4954. Min Act: -0.0000

Data Index: 199718 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5462. Min Act: -0.0000

Data Index: 319588 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4730. Min Act: -0.0000

Data Index: 425837 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1321726 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1690280 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1675302 (The Pile)

Max Activating Token Index: 703