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

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

Neuron 2597 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6394. Min Act: -0.0001

Data Index: 894434 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6807. Min Act: -0.0001

Data Index: 1198085 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6488. Min Act: -0.0001

Data Index: 1250009 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6376. Min Act: -0.0001

Data Index: 1189242 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6348. Min Act: -0.0001

Data Index: 903947 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6035. Min Act: -0.0001

Data Index: 1110314 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6128. Min Act: -0.0001

Data Index: 893604 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6395. Min Act: -0.0001

Data Index: 1108011 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6293. Min Act: -0.0001

Data Index: 136789 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6285. Min Act: -0.0001

Data Index: 889529 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6016. Min Act: -0.0001

Data Index: 492648 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5997. Min Act: -0.0001

Data Index: 826180 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5754. Min Act: -0.0001

Data Index: 44831 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6117. Min Act: -0.0001

Data Index: 173236 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5417. Min Act: -0.0001

Data Index: 1196027 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5904. Min Act: -0.0001

Data Index: 901008 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5699. Min Act: -0.0001

Data Index: 118123 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5695. Min Act: -0.0001

Data Index: 497530 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5468. Min Act: -0.0001

Data Index: 996944 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5506. Min Act: -0.0001

Data Index: 346017 (C4 (Web Text))

Max Activating Token Index: 433