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

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

Neuron 3788 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.7168. Min Act: -0.0001

Data Index: 1512042 (Python Code)

Max Activating Token Index: 969

Text #1

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6588. Min Act: -0.0001

Data Index: 1388973 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1504861 (Python Code)

Max Activating Token Index: 775

Text #3

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1475037 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6047. Min Act: -0.0001

Data Index: 1603092 (Python Code)

Max Activating Token Index: 930

Text #5

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1507849 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5797. Min Act: -0.0001

Data Index: 1594764 (Python Code)

Max Activating Token Index: 589

Text #7

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6330. Min Act: 0.0000

Data Index: 1380567 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1538201 (Python Code)

Max Activating Token Index: 356

Text #9

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5996. Min Act: -0.0001

Data Index: 1430145 (Python Code)

Max Activating Token Index: 987

Text #10

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5932. Min Act: -0.0001

Data Index: 1531550 (Python Code)

Max Activating Token Index: 620

Text #11

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5414. Min Act: -0.0001

Data Index: 1393492 (Python Code)

Max Activating Token Index: 699

Text #12

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1501315 (Python Code)

Max Activating Token Index: 654

Text #13

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1458946 (Python Code)

Max Activating Token Index: 865

Text #14

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5304. Min Act: -0.0001

Data Index: 1480618 (Python Code)

Max Activating Token Index: 624

Text #15

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1554027 (Python Code)

Max Activating Token Index: 90

Text #16

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1419485 (Python Code)

Max Activating Token Index: 484

Text #17

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1454606 (Python Code)

Max Activating Token Index: 595

Text #18

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5200. Min Act: -0.0001

Data Index: 1604947 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1489342 (Python Code)

Max Activating Token Index: 759