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

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

Neuron 5708 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.7731. Min Act: -0.0001

Data Index: 1368979 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.6549. Min Act: -0.0001

Data Index: 1420962 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.5467. Min Act: -0.0001

Data Index: 1655623 (Python Code)

Max Activating Token Index: 441

Text #3

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.5507. Min Act: -0.0001

Data Index: 1534353 (Python Code)

Max Activating Token Index: 155

Text #4

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.4479. Min Act: -0.0001

Data Index: 1459686 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.2937. Min Act: -0.0001

Data Index: 1361487 (Python Code)

Max Activating Token Index: 910

Text #6

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.2925. Min Act: -0.0001

Data Index: 1399829 (Python Code)

Max Activating Token Index: 346

Text #7

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.3164. Min Act: -0.0001

Data Index: 1636550 (Python Code)

Max Activating Token Index: 514

Text #8

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.3274. Min Act: -0.0001

Data Index: 1384340 (Python Code)

Max Activating Token Index: 893

Text #9

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.2998. Min Act: -0.0001

Data Index: 1567664 (Python Code)

Max Activating Token Index: 798

Text #10

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.1168. Min Act: -0.0001

Data Index: 1606160 (Python Code)

Max Activating Token Index: 502

Text #11

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.2251. Min Act: -0.0001

Data Index: 1399643 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.2310. Min Act: -0.0001

Data Index: 1607981 (Python Code)

Max Activating Token Index: 314

Text #13

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.2245. Min Act: -0.0001

Data Index: 1477937 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.1689. Min Act: -0.0001

Data Index: 1512748 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.1183. Min Act: -0.0001

Data Index: 1459110 (Python Code)

Max Activating Token Index: 353

Text #16

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.1404. Min Act: -0.0001

Data Index: 1442623 (Python Code)

Max Activating Token Index: 159

Text #17

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.0307. Min Act: -0.0001

Data Index: 1641568 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.0435. Min Act: -0.0001

Data Index: 1514991 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 1.7731. Min Range: -1.7731

Max Act: 1.0309. Min Act: -0.0001

Data Index: 1406955 (Python Code)

Max Activating Token Index: 100