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

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

Neuron 4923 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1558364 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1562285 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1371394 (Python Code)

Max Activating Token Index: 95

Text #3

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1468559 (Python Code)

Max Activating Token Index: 340

Text #4

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1477883 (Python Code)

Max Activating Token Index: 138

Text #5

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1433118 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1470298 (Python Code)

Max Activating Token Index: 279

Text #7

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1451941 (Python Code)

Max Activating Token Index: 134

Text #8

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1640543 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1393877 (Python Code)

Max Activating Token Index: 397

Text #10

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1448105 (Python Code)

Max Activating Token Index: 109

Text #11

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1419908 (Python Code)

Max Activating Token Index: 47

Text #12

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1541600 (Python Code)

Max Activating Token Index: 558

Text #13

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1509170 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1411682 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1568720 (Python Code)

Max Activating Token Index: 366

Text #16

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1383513 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1620863 (Python Code)

Max Activating Token Index: 565

Text #18

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1471813 (Python Code)

Max Activating Token Index: 349

Text #19

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1451431 (Python Code)

Max Activating Token Index: 576