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

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

Neuron 2097 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8100. Min Act: -0.0001

Data Index: 1059053 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8205. Min Act: -0.0001

Data Index: 915907 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8325. Min Act: -0.0001

Data Index: 828048 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7656. Min Act: -0.0001

Data Index: 50195 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7535. Min Act: -0.0001

Data Index: 752307 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7324. Min Act: -0.0001

Data Index: 592845 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6591. Min Act: -0.0001

Data Index: 1303741 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6945. Min Act: -0.0001

Data Index: 878685 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6922. Min Act: -0.0001

Data Index: 507495 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6720. Min Act: -0.0001

Data Index: 1347787 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6367. Min Act: -0.0001

Data Index: 526847 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6589. Min Act: -0.0001

Data Index: 287802 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6556. Min Act: -0.0001

Data Index: 728718 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6887. Min Act: -0.0001

Data Index: 956471 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7267. Min Act: -0.0001

Data Index: 828510 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6443. Min Act: -0.0001

Data Index: 752901 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6835. Min Act: -0.0001

Data Index: 767432 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6903. Min Act: -0.0001

Data Index: 473654 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6309. Min Act: -0.0001

Data Index: 83132 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6293. Min Act: -0.0001

Data Index: 90926 (C4 (Web Text))

Max Activating Token Index: 747