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

Dataset: The Pile

Neuron 2950 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: 0.4954. Min Range: -0.4954

Max Act: 0.4954. Min Act: -0.0000

Data Index: 1206943 (The Pile)

Max Activating Token Index: 111

Text #1

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4925. Min Act: -0.0000

Data Index: 451601 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1633406 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4421. Min Act: -0.0000

Data Index: 854517 (The Pile)

Max Activating Token Index: 86

Text #4

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4381. Min Act: -0.0000

Data Index: 180779 (The Pile)

Max Activating Token Index: 7

Text #5

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1621475 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4611. Min Act: -0.0000

Data Index: 141280 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1432782 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1983470 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4415. Min Act: -0.0000

Data Index: 980255 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4407. Min Act: -0.0000

Data Index: 403740 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1979399 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4201. Min Act: -0.0000

Data Index: 135075 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4314. Min Act: -0.0000

Data Index: 656901 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1590824 (The Pile)

Max Activating Token Index: 69

Text #15

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1867411 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4458. Min Act: -0.0000

Data Index: 987704 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4134. Min Act: -0.0000

Data Index: 216869 (The Pile)

Max Activating Token Index: 39

Text #18

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4122. Min Act: -0.0000

Data Index: 129445 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1987515 (The Pile)

Max Activating Token Index: 406