Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2663 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.6170. Min Range: -8.6170

Max Act: 8.6170. Min Act: -0.0000

Data Index: 121132 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 8.6170. Min Range: -8.6170

Max Act: 8.5355. Min Act: -0.0000

Data Index: 1118733 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 8.6170. Min Range: -8.6170

Max Act: 8.4430. Min Act: -0.0000

Data Index: 529190 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 8.6170. Min Range: -8.6170

Max Act: 8.0591. Min Act: -0.0000

Data Index: 861144 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 8.6170. Min Range: -8.6170

Max Act: 8.1460. Min Act: -0.0000

Data Index: 1353556 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 8.6170. Min Range: -8.6170

Max Act: 8.1295. Min Act: -0.0000

Data Index: 353911 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 8.6170. Min Range: -8.6170

Max Act: 8.0905. Min Act: -0.0000

Data Index: 1010844 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 8.6170. Min Range: -8.6170

Max Act: 7.9079. Min Act: -0.0000

Data Index: 262507 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 8.6170. Min Range: -8.6170

Max Act: 7.8902. Min Act: -0.0000

Data Index: 942033 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 8.6170. Min Range: -8.6170

Max Act: 7.9028. Min Act: -0.0000

Data Index: 1204046 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 8.6170. Min Range: -8.6170

Max Act: 8.1920. Min Act: -0.0000

Data Index: 282843 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 8.6170. Min Range: -8.6170

Max Act: 8.0045. Min Act: -0.0000

Data Index: 1317862 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 8.6170. Min Range: -8.6170

Max Act: 7.7971. Min Act: -0.0000

Data Index: 907244 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 8.6170. Min Range: -8.6170

Max Act: 7.9817. Min Act: -0.0000

Data Index: 703925 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 8.6170. Min Range: -8.6170

Max Act: 7.8011. Min Act: -0.0000

Data Index: 261863 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 8.6170. Min Range: -8.6170

Max Act: 8.1209. Min Act: -0.0000

Data Index: 946115 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 8.6170. Min Range: -8.6170

Max Act: 7.9445. Min Act: -0.0000

Data Index: 1019354 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 8.6170. Min Range: -8.6170

Max Act: 7.7421. Min Act: -0.0000

Data Index: 806198 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 8.6170. Min Range: -8.6170

Max Act: 7.7304. Min Act: -0.0000

Data Index: 1164160 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 8.6170. Min Range: -8.6170

Max Act: 7.7189. Min Act: -0.0000

Data Index: 425131 (C4 (Web Text))

Max Activating Token Index: 228