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

Dataset: The Pile

Neuron 844 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: 0.7930. Min Range: -0.7930

Max Act: 0.7930. Min Act: -0.0000

Data Index: 198182 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1751698 (The Pile)

Max Activating Token Index: 55

Text #2

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1165249 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1767754 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5888. Min Act: -0.0000

Data Index: 802279 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1459818 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5703. Min Act: -0.0000

Data Index: 459912 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1105649 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1005792 (The Pile)

Max Activating Token Index: 788

Text #9

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5588. Min Act: -0.0000

Data Index: 333300 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1330061 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1143955 (The Pile)

Max Activating Token Index: 462

Text #12

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5110. Min Act: -0.0000

Data Index: 933548 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.4767. Min Act: -0.0000

Data Index: 922809 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1091324 (The Pile)

Max Activating Token Index: 535

Text #15

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1183064 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1785393 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1538468 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.5247. Min Act: -0.0000

Data Index: 629934 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.4922. Min Act: -0.0000

Data Index: 976419 (The Pile)

Max Activating Token Index: 815