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

Dataset: The Pile

Neuron 2498 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.4886. Min Act: -0.0000

Data Index: 1001137 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2800. Min Act: -0.0000

Data Index: 161149 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1041. Min Act: -0.0000

Data Index: 767341 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1069069 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1250. Min Act: -0.0000

Data Index: 724495 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1511323 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1272. Min Act: -0.0000

Data Index: 259375 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1506. Min Act: -0.0000

Data Index: 1035853 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0511. Min Act: -0.0000

Data Index: 129730 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0520. Min Act: -0.0000

Data Index: 751722 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1915000 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8605. Min Act: -0.0000

Data Index: 966101 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9100. Min Act: -0.0000

Data Index: 349817 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1984574 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1582424 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8580. Min Act: -0.0000

Data Index: 535557 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1804367 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8630. Min Act: -0.0000

Data Index: 865753 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8116. Min Act: -0.0000

Data Index: 629610 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1136992 (The Pile)

Max Activating Token Index: 204