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

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

Neuron 4796 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1387. Min Range: -1.1387

Max Act: 1.1387. Min Act: -0.0000

Data Index: 637985 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 1.1387. Min Range: -1.1387

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1103228 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 1.1387. Min Range: -1.1387

Max Act: 1.0738. Min Act: -0.0000

Data Index: 456239 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 1.1387. Min Range: -1.1387

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1055798 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.9324. Min Act: -0.0000

Data Index: 317334 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1198756 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8645. Min Act: -0.0000

Data Index: 204348 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8524. Min Act: -0.0000

Data Index: 480561 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8933. Min Act: -0.0000

Data Index: 134363 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1201501 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8344. Min Act: -0.0000

Data Index: 80529 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8265. Min Act: -0.0000

Data Index: 405417 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8254. Min Act: -0.0000

Data Index: 405104 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8100. Min Act: -0.0000

Data Index: 874603 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8536. Min Act: -0.0000

Data Index: 575237 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8565. Min Act: -0.0000

Data Index: 12164 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.7552. Min Act: -0.0000

Data Index: 33112 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.7872. Min Act: -0.0000

Data Index: 599467 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.7864. Min Act: -0.0000

Data Index: 483432 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1004287 (C4 (Web Text))

Max Activating Token Index: 336