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

Dataset: The Pile

Neuron 836 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1597218 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.6330. Min Act: -0.0000

Data Index: 62067 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.6094. Min Act: -0.0000

Data Index: 542570 (The Pile)

Max Activating Token Index: 932

Text #3

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1712258 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1293160 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.6417. Min Act: -0.0000

Data Index: 895757 (The Pile)

Max Activating Token Index: 704

Text #6

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1106779 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5144. Min Act: -0.0000

Data Index: 98546 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1301793 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.6022. Min Act: -0.0000

Data Index: 281396 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1541846 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4928. Min Act: -0.0000

Data Index: 427359 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1789868 (The Pile)

Max Activating Token Index: 606

Text #13

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4400. Min Act: -0.0000

Data Index: 774455 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1817416 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4937. Min Act: -0.0000

Data Index: 956322 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1456808 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4804. Min Act: -0.0000

Data Index: 223678 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1444382 (The Pile)

Max Activating Token Index: 31

Text #19

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1710483 (The Pile)

Max Activating Token Index: 102