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

Dataset: The Pile

Neuron 3020 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: 0.5483. Min Range: -0.5483

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1333791 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1200455 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1524344 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4299. Min Act: -0.0000

Data Index: 638171 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4494. Min Act: -0.0000

Data Index: 98395 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1340647 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4125. Min Act: -0.0000

Data Index: 149400 (The Pile)

Max Activating Token Index: 5

Text #7

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1903253 (The Pile)

Max Activating Token Index: 744

Text #8

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1691064 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4129. Min Act: -0.0000

Data Index: 479641 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1261570 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4093. Min Act: -0.0000

Data Index: 255122 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1274347 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1032083 (The Pile)

Max Activating Token Index: 932

Text #14

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.4034. Min Act: -0.0000

Data Index: 911130 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1368790 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1246259 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1237719 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1568738 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.5483. Min Range: -0.5483

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1118163 (The Pile)

Max Activating Token Index: 1021