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

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

Neuron 1539 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.6503. Min Act: -0.0000

Data Index: 1186251 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.5781. Min Act: -0.0000

Data Index: 599402 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.6881. Min Act: -0.0000

Data Index: 546909 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.3613. Min Act: -0.0000

Data Index: 933960 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.6081. Min Act: -0.0000

Data Index: 1090516 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.5150. Min Act: -0.0000

Data Index: 72474 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.2428. Min Act: -0.0000

Data Index: 436410 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.0973. Min Act: -0.0000

Data Index: 370567 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.1880. Min Act: -0.0000

Data Index: 630660 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.1657. Min Act: -0.0000

Data Index: 109316 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.1860. Min Act: -0.0000

Data Index: 370889 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.0398. Min Act: -0.0000

Data Index: 1045509 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.0328. Min Act: -0.0000

Data Index: 973320 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 2.6881. Min Range: -2.6881

Max Act: 1.9223. Min Act: -0.0000

Data Index: 99129 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.0039. Min Act: -0.0000

Data Index: 749498 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.0037. Min Act: -0.0000

Data Index: 645482 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 2.6881. Min Range: -2.6881

Max Act: 1.6802. Min Act: -0.0000

Data Index: 381298 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 2.6881. Min Range: -2.6881

Max Act: 1.9532. Min Act: -0.0000

Data Index: 1291992 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 2.6881. Min Range: -2.6881

Max Act: 2.0416. Min Act: -0.0000

Data Index: 402602 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 2.6881. Min Range: -2.6881

Max Act: 1.8139. Min Act: -0.0000

Data Index: 780764 (C4 (Web Text))

Max Activating Token Index: 830