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

Dataset: The Pile

Neuron 1149 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.6313. Min Act: -0.0000

Data Index: 180673 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3995. Min Act: -0.0000

Data Index: 138790 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4168. Min Act: -0.0000

Data Index: 1960389 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4758. Min Act: -0.0000

Data Index: 212830 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3819. Min Act: -0.0000

Data Index: 1002821 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3576. Min Act: -0.0000

Data Index: 580989 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3258. Min Act: -0.0000

Data Index: 1966449 (The Pile)

Max Activating Token Index: 563

Text #7

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1736673 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.2605. Min Act: -0.0000

Data Index: 634073 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.2259. Min Act: -0.0000

Data Index: 410985 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.2790. Min Act: -0.0000

Data Index: 1494225 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.1524. Min Act: -0.0000

Data Index: 1386249 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1522526 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1727879 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1124127 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.0779. Min Act: -0.0000

Data Index: 5363 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.0873. Min Act: -0.0000

Data Index: 814442 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.1405. Min Act: -0.0000

Data Index: 587672 (The Pile)

Max Activating Token Index: 253

Text #18

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1582182 (The Pile)

Max Activating Token Index: 368

Text #19

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.1350. Min Act: -0.0000

Data Index: 692436 (The Pile)

Max Activating Token Index: 297