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

Dataset: The Pile

Neuron 3002 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1813479 (The Pile)

Max Activating Token Index: 262

Text #1

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8268. Min Act: -0.0000

Data Index: 725011 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1462918 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1134628 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1493212 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7011. Min Act: -0.0000

Data Index: 723651 (The Pile)

Max Activating Token Index: 423

Text #6

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6826. Min Act: -0.0000

Data Index: 486530 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1849931 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6387. Min Act: -0.0000

Data Index: 654421 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1255849 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1366937 (The Pile)

Max Activating Token Index: 792

Text #11

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1004140 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5859. Min Act: -0.0000

Data Index: 152025 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1108161 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1496841 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6155. Min Act: -0.0000

Data Index: 281365 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6121. Min Act: -0.0000

Data Index: 782495 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1815005 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6274. Min Act: -0.0000

Data Index: 650565 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5858. Min Act: -0.0000

Data Index: 516574 (The Pile)

Max Activating Token Index: 775