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

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

Neuron 3870 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.7065. Min Act: -0.0002

Data Index: 330951 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.7109. Min Act: -0.0002

Data Index: 1141697 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.7003. Min Act: -0.0002

Data Index: 939527 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.6437. Min Act: -0.0002

Data Index: 971540 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.6623. Min Act: -0.0002

Data Index: 18292 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.6669. Min Act: -0.0002

Data Index: 78024 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.6595. Min Act: -0.0002

Data Index: 26823 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5995. Min Act: -0.0002

Data Index: 796013 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5534. Min Act: -0.0002

Data Index: 417537 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5651. Min Act: -0.0002

Data Index: 532055 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5571. Min Act: -0.0002

Data Index: 438260 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5149. Min Act: -0.0002

Data Index: 1122440 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5503. Min Act: -0.0002

Data Index: 754710 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5774. Min Act: -0.0002

Data Index: 1084407 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5025. Min Act: -0.0002

Data Index: 961783 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5290. Min Act: -0.0002

Data Index: 74691 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5368. Min Act: -0.0002

Data Index: 307611 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5225. Min Act: -0.0003

Data Index: 1147853 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.5043. Min Act: -0.0002

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 1.7109. Min Range: -1.7109

Max Act: 1.4755. Min Act: -0.0002

Data Index: 705364 (C4 (Web Text))

Max Activating Token Index: 619