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

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

Neuron 2786 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1345765 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1046959 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1322. Min Act: -0.0001

Data Index: 533834 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0899. Min Act: -0.0001

Data Index: 817847 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1104. Min Act: -0.0001

Data Index: 174512 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1019693 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0977. Min Act: -0.0001

Data Index: 224291 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1048929 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1233649 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0923. Min Act: -0.0001

Data Index: 441139 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0940. Min Act: -0.0001

Data Index: 236744 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0861. Min Act: -0.0001

Data Index: 232367 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0841. Min Act: -0.0001

Data Index: 671012 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0914. Min Act: -0.0000

Data Index: 115630 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0906. Min Act: -0.0000

Data Index: 471544 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0802. Min Act: -0.0000

Data Index: 561263 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0896. Min Act: -0.0001

Data Index: 673375 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0848. Min Act: -0.0000

Data Index: 925463 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0908. Min Act: -0.0000

Data Index: 314265 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1256748 (C4 (Web Text))

Max Activating Token Index: 994