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

Dataset: The Pile

Neuron 4898 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6945. Min Act: -0.0000

Data Index: 774372 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1890037 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1696663 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1707066 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1841599 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6106. Min Act: -0.0000

Data Index: 553373 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6221. Min Act: -0.0000

Data Index: 80223 (The Pile)

Max Activating Token Index: 288

Text #7

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1510074 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1682738 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5622. Min Act: -0.0000

Data Index: 990121 (The Pile)

Max Activating Token Index: 597

Text #10

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5615. Min Act: -0.0000

Data Index: 644361 (The Pile)

Max Activating Token Index: 858

Text #11

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1740189 (The Pile)

Max Activating Token Index: 835

Text #12

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1968447 (The Pile)

Max Activating Token Index: 881

Text #13

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1489688 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5447. Min Act: -0.0000

Data Index: 1532277 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5424. Min Act: -0.0000

Data Index: 182329 (The Pile)

Max Activating Token Index: 286

Text #16

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1236707 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6030. Min Act: -0.0000

Data Index: 882806 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1212479 (The Pile)

Max Activating Token Index: 898

Text #19

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1482697 (The Pile)

Max Activating Token Index: 287