Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4045 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7287. Min Act: -0.0000

Data Index: 351497 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7047. Min Act: -0.0000

Data Index: 792551 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1133258 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6856. Min Act: -0.0000

Data Index: 485447 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1197107 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1087025 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6933. Min Act: -0.0000

Data Index: 185524 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6442. Min Act: -0.0000

Data Index: 37366 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6090. Min Act: -0.0000

Data Index: 52096 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6467. Min Act: -0.0000

Data Index: 517661 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5694. Min Act: -0.0000

Data Index: 990132 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5241. Min Act: -0.0000

Data Index: 547147 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1270556 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4922. Min Act: -0.0000

Data Index: 856740 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5601. Min Act: -0.0000

Data Index: 375583 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5201. Min Act: -0.0000

Data Index: 861965 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4165. Min Act: -0.0000

Data Index: 734436 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4270. Min Act: -0.0000

Data Index: 72222 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4156. Min Act: -0.0000

Data Index: 401052 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4264. Min Act: -0.0000

Data Index: 314127 (C4 (Web Text))

Max Activating Token Index: 59