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

Dataset: The Pile

Neuron 2663 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: 0.9595. Min Range: -0.9595

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1369348 (The Pile)

Max Activating Token Index: 376

Text #1

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.7536. Min Act: -0.0001

Data Index: 1737829 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1591724 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.6728. Min Act: -0.0000

Data Index: 613841 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1476574 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1630918 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1005319 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5940. Min Act: -0.0000

Data Index: 661548 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5759. Min Act: -0.0000

Data Index: 151357 (The Pile)

Max Activating Token Index: 813

Text #9

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1994375 (The Pile)

Max Activating Token Index: 19

Text #10

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5912. Min Act: -0.0000

Data Index: 967154 (The Pile)

Max Activating Token Index: 526

Text #11

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1436178 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.6202. Min Act: -0.0000

Data Index: 924095 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5524. Min Act: -0.0000

Data Index: 458671 (The Pile)

Max Activating Token Index: 718

Text #14

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5830. Min Act: -0.0000

Data Index: 807870 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5263. Min Act: -0.0000

Data Index: 10214 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5604. Min Act: -0.0000

Data Index: 900523 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5736. Min Act: -0.0000

Data Index: 122345 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1180800 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 0.9595. Min Range: -0.9595

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1207673 (The Pile)

Max Activating Token Index: 983