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

Dataset: The Pile

Neuron 1478 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: 3.3993. Min Range: -3.3993

Max Act: 3.3993. Min Act: -0.0000

Data Index: 1970671 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.8803. Min Act: -0.0000

Data Index: 1810365 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.9589. Min Act: -0.0000

Data Index: 1245829 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.8241. Min Act: -0.0000

Data Index: 1026621 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.8221. Min Act: -0.0000

Data Index: 645493 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.8854. Min Act: -0.0000

Data Index: 1942318 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.8773. Min Act: -0.0000

Data Index: 1337148 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.7039. Min Act: -0.0000

Data Index: 1874399 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 3.3993. Min Range: -3.3993

Max Act: 3.0880. Min Act: -0.0000

Data Index: 1274117 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.7976. Min Act: -0.0000

Data Index: 962191 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.8101. Min Act: -0.0000

Data Index: 476854 (The Pile)

Max Activating Token Index: 960

Text #11

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.6226. Min Act: -0.0000

Data Index: 795345 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.5968. Min Act: -0.0000

Data Index: 1676607 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.8270. Min Act: -0.0000

Data Index: 469319 (The Pile)

Max Activating Token Index: 127

Text #14

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.8011. Min Act: -0.0000

Data Index: 224618 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.6517. Min Act: -0.0000

Data Index: 1817139 (The Pile)

Max Activating Token Index: 713

Text #16

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.4165. Min Act: -0.0000

Data Index: 1881993 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.6331. Min Act: -0.0000

Data Index: 1172296 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.5743. Min Act: -0.0000

Data Index: 1677175 (The Pile)

Max Activating Token Index: 298

Text #19

Max Range: 3.3993. Min Range: -3.3993

Max Act: 2.6827. Min Act: -0.0000

Data Index: 1382040 (The Pile)

Max Activating Token Index: 93