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

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

Neuron 572 in Layer 7

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: 755200 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 1.1387. Min Range: -1.1387

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1260201 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 1.1387. Min Range: -1.1387

Max Act: 1.0373. Min Act: -0.0000

Data Index: 1107870 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 1.1387. Min Range: -1.1387

Max Act: 1.0218. Min Act: -0.0000

Data Index: 352513 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 1.1387. Min Range: -1.1387

Max Act: 1.0090. Min Act: -0.0000

Data Index: 34922 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1267254 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1346326 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.9489. Min Act: -0.0000

Data Index: 27912 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8866. Min Act: -0.0000

Data Index: 431596 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.9170. Min Act: -0.0000

Data Index: 861928 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.9091. Min Act: -0.0000

Data Index: 155064 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1303299 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1288144 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8772. Min Act: -0.0000

Data Index: 240390 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1257696 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1216585 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1355381 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8336. Min Act: -0.0000

Data Index: 437732 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8562. Min Act: -0.0000

Data Index: 891681 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 1.1387. Min Range: -1.1387

Max Act: 0.8514. Min Act: -0.0000

Data Index: 756224 (C4 (Web Text))

Max Activating Token Index: 671