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

Dataset: The Pile

Neuron 807 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: 0.6335. Min Range: -0.6335

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1905293 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1049239 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5700. Min Act: -0.0000

Data Index: 150796 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1644906 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1167742 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1472133 (The Pile)

Max Activating Token Index: 855

Text #6

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5036. Min Act: -0.0000

Data Index: 736253 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5004. Min Act: -0.0000

Data Index: 536347 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4894. Min Act: -0.0000

Data Index: 393006 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1847731 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5116. Min Act: -0.0000

Data Index: 532795 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4656. Min Act: -0.0000

Data Index: 1611447 (The Pile)

Max Activating Token Index: 925

Text #12

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1096393 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4888. Min Act: -0.0000

Data Index: 124045 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5057. Min Act: -0.0000

Data Index: 120678 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1370103 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5007. Min Act: -0.0000

Data Index: 46713 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4531. Min Act: -0.0000

Data Index: 577348 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4567. Min Act: -0.0000

Data Index: 960859 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1891965 (The Pile)

Max Activating Token Index: 335