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

Dataset: The Pile

Neuron 4017 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: 1.3410. Min Range: -1.3410

Max Act: 1.3410. Min Act: -0.0000

Data Index: 199949 (The Pile)

Max Activating Token Index: 416

Text #1

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.1702. Min Act: 0.0000

Data Index: 1959662 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.1538. Min Act: -0.0000

Data Index: 1288390 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.1541. Min Act: -0.0000

Data Index: 865244 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.1298. Min Act: 0.0000

Data Index: 1140314 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1792094 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1813538 (The Pile)

Max Activating Token Index: 320

Text #7

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1601589 (The Pile)

Max Activating Token Index: 885

Text #8

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1430600 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1524083 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9324. Min Act: 0.0000

Data Index: 1228164 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1780212 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9661. Min Act: -0.0000

Data Index: 767222 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.8553. Min Act: -0.0000

Data Index: 521132 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9426. Min Act: -0.0000

Data Index: 586969 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1144371 (The Pile)

Max Activating Token Index: 637

Text #16

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.6999. Min Act: -0.0000

Data Index: 979514 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.7537. Min Act: -0.0000

Data Index: 796472 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.8557. Min Act: 0.0000

Data Index: 1781075 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.7415. Min Act: -0.0000

Data Index: 308832 (The Pile)

Max Activating Token Index: 612