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

Dataset: The Pile

Neuron 2819 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1678540 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8426. Min Act: 0.0000

Data Index: 972317 (The Pile)

Max Activating Token Index: 178

Text #2

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1225306 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7244. Min Act: -0.0000

Data Index: 127581 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7558. Min Act: -0.0000

Data Index: 943779 (The Pile)

Max Activating Token Index: 699

Text #5

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1725774 (The Pile)

Max Activating Token Index: 128

Text #6

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7083. Min Act: -0.0000

Data Index: 55793 (The Pile)

Max Activating Token Index: 830

Text #7

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7571. Min Act: -0.0000

Data Index: 789006 (The Pile)

Max Activating Token Index: 127

Text #8

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6958. Min Act: -0.0000

Data Index: 545108 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1193478 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1440280 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7044. Min Act: -0.0000

Data Index: 313667 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6867. Min Act: -0.0000

Data Index: 397440 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6392. Min Act: -0.0000

Data Index: 580804 (The Pile)

Max Activating Token Index: 952

Text #14

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1870887 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6090. Min Act: -0.0000

Data Index: 105486 (The Pile)

Max Activating Token Index: 702

Text #16

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1782660 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1774099 (The Pile)

Max Activating Token Index: 103

Text #18

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6317. Min Act: -0.0000

Data Index: 856412 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1174063 (The Pile)

Max Activating Token Index: 236