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

Dataset: The Pile

Neuron 3260 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: 0.7880. Min Range: -0.7880

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1722062 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1003466 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1902929 (The Pile)

Max Activating Token Index: 139

Text #3

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1022892 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5841. Min Act: -0.0000

Data Index: 997110 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1623044 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1155374 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5638. Min Act: -0.0000

Data Index: 603101 (The Pile)

Max Activating Token Index: 48

Text #8

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5781. Min Act: -0.0000

Data Index: 863409 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1293954 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5828. Min Act: -0.0000

Data Index: 628338 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5833. Min Act: -0.0000

Data Index: 313410 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1509305 (The Pile)

Max Activating Token Index: 944

Text #13

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1083751 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1956095 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1792066 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1771431 (The Pile)

Max Activating Token Index: 706

Text #17

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1217451 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1116237 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1230873 (The Pile)

Max Activating Token Index: 994