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

Dataset: The Pile

Neuron 3554 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: 0.8219. Min Range: -0.8219

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1082694 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7491. Min Act: -0.0000

Data Index: 330076 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7105. Min Act: -0.0000

Data Index: 904250 (The Pile)

Max Activating Token Index: 433

Text #3

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1869072 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1159848 (The Pile)

Max Activating Token Index: 360

Text #5

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1760510 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7580. Min Act: -0.0000

Data Index: 970926 (The Pile)

Max Activating Token Index: 999

Text #7

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.8080. Min Act: -0.0000

Data Index: 295818 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1500948 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1690715 (The Pile)

Max Activating Token Index: 375

Text #10

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6792. Min Act: -0.0000

Data Index: 728122 (The Pile)

Max Activating Token Index: 625

Text #11

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.8155. Min Act: -0.0000

Data Index: 78542 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.8083. Min Act: -0.0000

Data Index: 358804 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7837. Min Act: -0.0000

Data Index: 127261 (The Pile)

Max Activating Token Index: 937

Text #14

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1377201 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1894815 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1966085 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7381. Min Act: -0.0000

Data Index: 470530 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7917. Min Act: -0.0000

Data Index: 755413 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1777997 (The Pile)

Max Activating Token Index: 183