Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2771 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1701356 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1555725 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4306. Min Act: -0.0000

Data Index: 196728 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1960497 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4040. Min Act: -0.0000

Data Index: 882663 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1220691 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1243922 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1960832 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4003. Min Act: -0.0000

Data Index: 938275 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3728. Min Act: -0.0000

Data Index: 352507 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1524039 (The Pile)

Max Activating Token Index: 977

Text #11

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1184235 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3993. Min Act: -0.0000

Data Index: 899961 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1032343 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1443537 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3557. Min Act: -0.0000

Data Index: 667871 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3940. Min Act: -0.0000

Data Index: 18829 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3901. Min Act: -0.0000

Data Index: 528977 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4186. Min Act: -0.0000

Data Index: 737523 (The Pile)

Max Activating Token Index: 638

Text #19

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1898306 (The Pile)

Max Activating Token Index: 130