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

Dataset: The Pile

Neuron 2775 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1656744 (The Pile)

Max Activating Token Index: 357

Text #1

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.6117. Min Act: -0.0000

Data Index: 690782 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1129522 (The Pile)

Max Activating Token Index: 306

Text #3

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5953. Min Act: -0.0000

Data Index: 464560 (The Pile)

Max Activating Token Index: 231

Text #4

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5413. Min Act: -0.0000

Data Index: 274107 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1144335 (The Pile)

Max Activating Token Index: 326

Text #6

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.4618. Min Act: -0.0000

Data Index: 232825 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1605699 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1474730 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1344931 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1230356 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5012. Min Act: -0.0000

Data Index: 749236 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1098392 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.4915. Min Act: -0.0000

Data Index: 811767 (The Pile)

Max Activating Token Index: 906

Text #14

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1948998 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.4811. Min Act: -0.0000

Data Index: 332436 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.4982. Min Act: -0.0000

Data Index: 569871 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1995228 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1780977 (The Pile)

Max Activating Token Index: 909

Text #19

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.4909. Min Act: -0.0000

Data Index: 330856 (The Pile)

Max Activating Token Index: 918