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

Dataset: The Pile

Neuron 2558 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: 0.8058. Min Range: -0.8058

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1632316 (The Pile)

Max Activating Token Index: 198

Text #1

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1398768 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6787. Min Act: -0.0000

Data Index: 607876 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1598098 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1237538 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6699. Min Act: -0.0000

Data Index: 460884 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1447206 (The Pile)

Max Activating Token Index: 834

Text #7

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7237. Min Act: -0.0000

Data Index: 727976 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1458087 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6734. Min Act: -0.0000

Data Index: 150606 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6470. Min Act: -0.0000

Data Index: 278099 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6157. Min Act: -0.0000

Data Index: 792459 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.5753. Min Act: -0.0000

Data Index: 229495 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6653. Min Act: -0.0000

Data Index: 492143 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6032. Min Act: -0.0000

Data Index: 504175 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1455314 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.5780. Min Act: -0.0000

Data Index: 379743 (The Pile)

Max Activating Token Index: 561

Text #17

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1810118 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1761908 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6271. Min Act: -0.0000

Data Index: 410693 (The Pile)

Max Activating Token Index: 726