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

Dataset: The Pile

Neuron 2280 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.6235. Min Act: -0.0000

Data Index: 573056 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1382689 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1945862 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1065842 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1205298 (The Pile)

Max Activating Token Index: 753

Text #5

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5689. Min Act: -0.0000

Data Index: 612599 (The Pile)

Max Activating Token Index: 528

Text #6

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5244. Min Act: -0.0000

Data Index: 311407 (The Pile)

Max Activating Token Index: 804

Text #7

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5560. Min Act: -0.0000

Data Index: 957540 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1265140 (The Pile)

Max Activating Token Index: 604

Text #9

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1624431 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1674881 (The Pile)

Max Activating Token Index: 847

Text #11

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1092013 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1634930 (The Pile)

Max Activating Token Index: 624

Text #13

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4963. Min Act: -0.0000

Data Index: 264555 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1600234 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1144644 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4794. Min Act: -0.0000

Data Index: 117510 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4618. Min Act: -0.0000

Data Index: 38291 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1378954 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1471262 (The Pile)

Max Activating Token Index: 387