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

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

Neuron 4436 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: 1.3680. Min Range: -1.3680

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1585824 (Python Code)

Max Activating Token Index: 855

Text #1

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1444904 (Python Code)

Max Activating Token Index: 420

Text #2

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1567331 (Python Code)

Max Activating Token Index: 979

Text #3

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1503931 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.0226. Min Act: -0.0000

Data Index: 1579345 (Python Code)

Max Activating Token Index: 798

Text #5

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1515285 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1586280 (Python Code)

Max Activating Token Index: 193

Text #7

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1603836 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1370224 (Python Code)

Max Activating Token Index: 589

Text #9

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1605152 (Python Code)

Max Activating Token Index: 331

Text #10

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1457317 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1401611 (Python Code)

Max Activating Token Index: 366

Text #12

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1482110 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1384134 (Python Code)

Max Activating Token Index: 371

Text #14

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1536083 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1379711 (Python Code)

Max Activating Token Index: 293

Text #16

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1599823 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.8201. Min Act: -0.0000

Data Index: 1535556 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1605277 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 1.3680. Min Range: -1.3680

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1655422 (Python Code)

Max Activating Token Index: 732