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

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

Neuron 1302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.9490. Min Act: -0.0001

Data Index: 1434672 (Python Code)

Max Activating Token Index: 83

Text #1

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8628. Min Act: -0.0001

Data Index: 1555933 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8299. Min Act: -0.0001

Data Index: 1593560 (Python Code)

Max Activating Token Index: 444

Text #3

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.7595. Min Act: -0.0001

Data Index: 1566184 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.7872. Min Act: -0.0001

Data Index: 1514450 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.6578. Min Act: -0.0001

Data Index: 1367123 (Python Code)

Max Activating Token Index: 332

Text #6

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.6515. Min Act: -0.0001

Data Index: 1561636 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1416503 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.6080. Min Act: -0.0001

Data Index: 1526444 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.6319. Min Act: -0.0001

Data Index: 1513646 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.5896. Min Act: -0.0001

Data Index: 1612035 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1556583 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.6020. Min Act: -0.0001

Data Index: 1565430 (Python Code)

Max Activating Token Index: 658

Text #13

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.5985. Min Act: -0.0001

Data Index: 1522719 (Python Code)

Max Activating Token Index: 980

Text #14

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.4855. Min Act: -0.0001

Data Index: 1634414 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1437266 (Python Code)

Max Activating Token Index: 506

Text #16

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.5636. Min Act: -0.0001

Data Index: 1581605 (Python Code)

Max Activating Token Index: 142

Text #17

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1484762 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.6136. Min Act: -0.0001

Data Index: 1536550 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.6333. Min Act: -0.0001

Data Index: 1402022 (Python Code)

Max Activating Token Index: 688