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

Dataset: The Pile

Neuron 1625 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.1850. Min Range: -10.1850

Max Act: 10.1850. Min Act: -0.0000

Data Index: 91780 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 10.1850. Min Range: -10.1850

Max Act: 10.1082. Min Act: -0.0000

Data Index: 1127803 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.7785. Min Act: -0.0000

Data Index: 1863097 (The Pile)

Max Activating Token Index: 609

Text #3

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.6445. Min Act: -0.0000

Data Index: 1991348 (The Pile)

Max Activating Token Index: 75

Text #4

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.6867. Min Act: -0.0000

Data Index: 1974181 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.4780. Min Act: -0.0000

Data Index: 1555753 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.5371. Min Act: -0.0000

Data Index: 861680 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.4779. Min Act: -0.0000

Data Index: 1851772 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.3059. Min Act: -0.0000

Data Index: 1285170 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.5104. Min Act: -0.0000

Data Index: 1924734 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.4918. Min Act: -0.0000

Data Index: 1433183 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.2049. Min Act: -0.0000

Data Index: 1893214 (The Pile)

Max Activating Token Index: 563

Text #12

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.4604. Min Act: -0.0000

Data Index: 1801826 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 10.1850. Min Range: -10.1850

Max Act: 8.9061. Min Act: -0.0000

Data Index: 475832 (The Pile)

Max Activating Token Index: 917

Text #14

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.2470. Min Act: -0.0000

Data Index: 732746 (The Pile)

Max Activating Token Index: 245

Text #15

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.2847. Min Act: -0.0000

Data Index: 245794 (The Pile)

Max Activating Token Index: 992

Text #16

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.3258. Min Act: -0.0000

Data Index: 412137 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.3081. Min Act: -0.0000

Data Index: 959523 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 10.1850. Min Range: -10.1850

Max Act: 8.9631. Min Act: -0.0000

Data Index: 1646133 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 10.1850. Min Range: -10.1850

Max Act: 9.2368. Min Act: -0.0000

Data Index: 970578 (The Pile)

Max Activating Token Index: 387