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

Dataset: The Pile

Neuron 4941 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.1822. Min Act: -0.0000

Data Index: 50815 (The Pile)

Max Activating Token Index: 826

Text #1

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.4363. Min Act: -0.0000

Data Index: 202044 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.5699. Min Act: -0.0000

Data Index: 1495968 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.6771. Min Act: -0.0000

Data Index: 1728381 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.4219. Min Act: -0.0000

Data Index: 1500963 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.8022. Min Act: -0.0000

Data Index: 1588180 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.7935. Min Act: -0.0000

Data Index: 1437375 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.4017. Min Act: -0.0000

Data Index: 79340 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.7517. Min Act: -0.0000

Data Index: 1024371 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.3913. Min Act: -0.0000

Data Index: 1028549 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.3162. Min Act: -0.0000

Data Index: 1128797 (The Pile)

Max Activating Token Index: 356

Text #11

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.1864. Min Act: -0.0000

Data Index: 1344952 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.3161. Min Act: -0.0000

Data Index: 1782918 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.6600. Min Act: -0.0000

Data Index: 949726 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.2998. Min Act: -0.0000

Data Index: 1973392 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.1989. Min Act: -0.0000

Data Index: 475382 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 3.8022. Min Range: -3.8022

Max Act: 2.7598. Min Act: -0.0000

Data Index: 434964 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 3.8022. Min Range: -3.8022

Max Act: 2.9688. Min Act: -0.0000

Data Index: 1506412 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.0765. Min Act: -0.0000

Data Index: 353799 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 3.8022. Min Range: -3.8022

Max Act: 3.0458. Min Act: -0.0000

Data Index: 1076893 (The Pile)

Max Activating Token Index: 663