Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 962 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1727936 (The Pile)

Max Activating Token Index: 240

Text #1

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1852467 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4879. Min Act: -0.0000

Data Index: 855387 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4848. Min Act: -0.0000

Data Index: 258948 (The Pile)

Max Activating Token Index: 674

Text #4

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4633. Min Act: -0.0000

Data Index: 651527 (The Pile)

Max Activating Token Index: 952

Text #5

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4491. Min Act: -0.0000

Data Index: 337727 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.5004. Min Act: -0.0000

Data Index: 503563 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1124788 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4786. Min Act: -0.0000

Data Index: 746293 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1616465 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4222. Min Act: -0.0001

Data Index: 1498746 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1745944 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1396613 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1586011 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4274. Min Act: -0.0000

Data Index: 903091 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4407. Min Act: -0.0000

Data Index: 855617 (The Pile)

Max Activating Token Index: 689

Text #16

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.3753. Min Act: -0.0000

Data Index: 102999 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1799779 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1955440 (The Pile)

Max Activating Token Index: 872

Text #19

Max Range: 0.5030. Min Range: -0.5030

Max Act: 0.4107. Min Act: -0.0000

Data Index: 720215 (The Pile)

Max Activating Token Index: 799