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

Dataset: The Pile

Neuron 85 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1502308 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6045. Min Act: -0.0000

Data Index: 900133 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5953. Min Act: 0.0000

Data Index: 92850 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1240318 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1264124 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5939. Min Act: -0.0000

Data Index: 537101 (The Pile)

Max Activating Token Index: 350

Text #6

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5418. Min Act: -0.0000

Data Index: 562252 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5026. Min Act: -0.0000

Data Index: 343828 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4809. Min Act: -0.0000

Data Index: 885291 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5447. Min Act: -0.0000

Data Index: 66134 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1647875 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1442035 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1350483 (The Pile)

Max Activating Token Index: 792

Text #13

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5143. Min Act: -0.0000

Data Index: 663528 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4647. Min Act: -0.0000

Data Index: 593802 (The Pile)

Max Activating Token Index: 970

Text #15

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4843. Min Act: -0.0000

Data Index: 942908 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1109503 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1873251 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4493. Min Act: -0.0000

Data Index: 714573 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4841. Min Act: -0.0000

Data Index: 660889 (The Pile)

Max Activating Token Index: 643