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

Dataset: The Pile

Neuron 4886 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: 0.5883. Min Range: -0.5883

Max Act: 0.5813. Min Act: -0.0000

Data Index: 941521 (The Pile)

Max Activating Token Index: 740

Text #1

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1450215 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1534293 (The Pile)

Max Activating Token Index: 775

Text #3

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1782627 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4845. Min Act: -0.0000

Data Index: 904737 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1314075 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4484. Min Act: -0.0000

Data Index: 25251 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1421019 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1961049 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1584561 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4702. Min Act: -0.0000

Data Index: 888207 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4807. Min Act: -0.0000

Data Index: 150514 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4354. Min Act: -0.0000

Data Index: 16374 (The Pile)

Max Activating Token Index: 606

Text #13

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4411. Min Act: -0.0000

Data Index: 317440 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4691. Min Act: -0.0000

Data Index: 634585 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4003. Min Act: -0.0000

Data Index: 1889294 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4458. Min Act: -0.0000

Data Index: 985482 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1131110 (The Pile)

Max Activating Token Index: 538

Text #18

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4355. Min Act: -0.0000

Data Index: 835583 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1109974 (The Pile)

Max Activating Token Index: 930