Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 355 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1508536 (Python Code)

Max Activating Token Index: 210

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1170. Min Act: -0.0002

Data Index: 1481546 (Python Code)

Max Activating Token Index: 711

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1643257 (Python Code)

Max Activating Token Index: 872

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1621287 (Python Code)

Max Activating Token Index: 227

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1600432 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1435376 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1025. Min Act: 0.0001

Data Index: 1369080 (Python Code)

Max Activating Token Index: 943

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0951. Min Act: 0.0001

Data Index: 1589786 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1489385 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1006. Min Act: -0.0002

Data Index: 1474762 (Python Code)

Max Activating Token Index: 609

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1436619 (Python Code)

Max Activating Token Index: 557

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1417496 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1495744 (Python Code)

Max Activating Token Index: 700

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1544630 (Python Code)

Max Activating Token Index: 201

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1425965 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1587085 (Python Code)

Max Activating Token Index: 283

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1512273 (Python Code)

Max Activating Token Index: 607

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1453667 (Python Code)

Max Activating Token Index: 878

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1558580 (Python Code)

Max Activating Token Index: 317

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1502054 (Python Code)

Max Activating Token Index: 792