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

Dataset: The Pile

Neuron 2439 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.6037. Min Act: -0.0000

Data Index: 96117 (The Pile)

Max Activating Token Index: 555

Text #1

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1033411 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.6539. Min Act: -0.0000

Data Index: 273774 (The Pile)

Max Activating Token Index: 868

Text #3

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.6110. Min Act: -0.0000

Data Index: 126131 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.6086. Min Act: -0.0000

Data Index: 969211 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5657. Min Act: -0.0000

Data Index: 376554 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1311522 (The Pile)

Max Activating Token Index: 582

Text #7

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1965667 (The Pile)

Max Activating Token Index: 644

Text #8

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5716. Min Act: -0.0000

Data Index: 539342 (The Pile)

Max Activating Token Index: 49

Text #9

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5796. Min Act: -0.0000

Data Index: 749327 (The Pile)

Max Activating Token Index: 671

Text #10

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1970507 (The Pile)

Max Activating Token Index: 235

Text #11

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1070318 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1457959 (The Pile)

Max Activating Token Index: 631

Text #13

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5856. Min Act: -0.0000

Data Index: 327869 (The Pile)

Max Activating Token Index: 232

Text #14

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5287. Min Act: -0.0000

Data Index: 969575 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5434. Min Act: -0.0000

Data Index: 148624 (The Pile)

Max Activating Token Index: 417

Text #16

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5459. Min Act: -0.0000

Data Index: 206143 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5402. Min Act: -0.0000

Data Index: 908771 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5246. Min Act: -0.0000

Data Index: 896690 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 0.6539. Min Range: -0.6539

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1665778 (The Pile)

Max Activating Token Index: 493