Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1803 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.6387. Min Act: -0.0000

Data Index: 593930 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5825. Min Act: -0.0000

Data Index: 674407 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1167802 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4921. Min Act: -0.0000

Data Index: 455614 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5062. Min Act: -0.0000

Data Index: 586835 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1188205 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1002348 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4510. Min Act: -0.0000

Data Index: 313161 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1079295 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4820. Min Act: -0.0000

Data Index: 281377 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1298127 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4529. Min Act: -0.0000

Data Index: 882508 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4468. Min Act: -0.0000

Data Index: 690954 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1097298 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4504. Min Act: -0.0000

Data Index: 802175 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4608. Min Act: -0.0000

Data Index: 194912 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1220703 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1336534 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4408. Min Act: -0.0000

Data Index: 547982 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4514. Min Act: -0.0000

Data Index: 529244 (C4 (Web Text))

Max Activating Token Index: 865