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

Dataset: The Pile

Neuron 2052 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.4040. Min Act: -0.0000

Data Index: 676193 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.2807. Min Act: -0.0000

Data Index: 1343688 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1227. Min Act: -0.0000

Data Index: 871427 (The Pile)

Max Activating Token Index: 847

Text #3

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1940. Min Act: -0.0000

Data Index: 1580928 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1608171 (The Pile)

Max Activating Token Index: 430

Text #5

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.0976. Min Act: -0.0000

Data Index: 21494 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1490513 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1412465 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1142. Min Act: -0.0000

Data Index: 513075 (The Pile)

Max Activating Token Index: 408

Text #9

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1077. Min Act: -0.0000

Data Index: 262142 (The Pile)

Max Activating Token Index: 572

Text #10

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1103. Min Act: -0.0000

Data Index: 985713 (The Pile)

Max Activating Token Index: 459

Text #11

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1343935 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.0703. Min Act: -0.0000

Data Index: 245329 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1771. Min Act: -0.0000

Data Index: 75051 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1765729 (The Pile)

Max Activating Token Index: 999

Text #15

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.0416. Min Act: -0.0000

Data Index: 1132764 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1600715 (The Pile)

Max Activating Token Index: 625

Text #17

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.0889. Min Act: -0.0000

Data Index: 1343561 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1404666 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.0813. Min Act: -0.0000

Data Index: 523084 (The Pile)

Max Activating Token Index: 327