Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 956 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1387. Min Act: -0.0001

Data Index: 458710 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1486034 (Python Code)

Max Activating Token Index: 864

Text #2

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1238. Min Act: -0.0001

Data Index: 467420 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1172. Min Act: -0.0001

Data Index: 849908 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1234. Min Act: -0.0001

Data Index: 501064 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1137158 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1608011 (Python Code)

Max Activating Token Index: 700

Text #7

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1050. Min Act: -0.0001

Data Index: 339366 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1148. Min Act: -0.0001

Data Index: 719989 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1371105 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1051. Min Act: -0.0001

Data Index: 832332 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1610420 (Python Code)

Max Activating Token Index: 368

Text #12

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1561837 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1026. Min Act: -0.0001

Data Index: 634832 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1325966 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0994. Min Act: -0.0001

Data Index: 367521 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1031. Min Act: -0.0001

Data Index: 340016 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1017. Min Act: -0.0001

Data Index: 1593126 (Python Code)

Max Activating Token Index: 892

Text #18

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0962. Min Act: -0.0001

Data Index: 853306 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0995. Min Act: -0.0001

Data Index: 346940 (C4 (Web Text))

Max Activating Token Index: 695