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

Dataset: The Pile

Neuron 3456 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: 0.8304. Min Range: -0.8304

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1823748 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.7762. Min Act: -0.0000

Data Index: 534941 (The Pile)

Max Activating Token Index: 152

Text #2

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1304631 (The Pile)

Max Activating Token Index: 949

Text #3

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.7012. Min Act: -0.0000

Data Index: 829893 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1515417 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1720063 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1886038 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1649596 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1837782 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1754983 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1739667 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.5471. Min Act: -0.0000

Data Index: 567963 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.5745. Min Act: -0.0000

Data Index: 231447 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.6320. Min Act: -0.0000

Data Index: 622459 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1163909 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1382061 (The Pile)

Max Activating Token Index: 527

Text #16

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.5768. Min Act: -0.0000

Data Index: 114653 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.5608. Min Act: -0.0001

Data Index: 534518 (The Pile)

Max Activating Token Index: 908

Text #18

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1557646 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 0.8304. Min Range: -0.8304

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1614095 (The Pile)

Max Activating Token Index: 714