Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 457 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4884. Min Act: -0.0000

Data Index: 928998 (The Pile)

Max Activating Token Index: 541

Text #1

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.5000. Min Act: -0.0001

Data Index: 738571 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4752. Min Act: -0.0000

Data Index: 153522 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1812270 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4368. Min Act: -0.0000

Data Index: 373546 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4239. Min Act: -0.0000

Data Index: 517793 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1130085 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4454. Min Act: -0.0001

Data Index: 1873617 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1743539 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4139. Min Act: -0.0000

Data Index: 412837 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1974275 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4028. Min Act: -0.0001

Data Index: 570227 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4027. Min Act: -0.0001

Data Index: 1602572 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3994. Min Act: -0.0001

Data Index: 1501777 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3927. Min Act: -0.0001

Data Index: 55935 (The Pile)

Max Activating Token Index: 657

Text #15

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4046. Min Act: -0.0000

Data Index: 349174 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1440985 (The Pile)

Max Activating Token Index: 473

Text #17

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3868. Min Act: -0.0001

Data Index: 511157 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1637438 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1814473 (The Pile)

Max Activating Token Index: 967