Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 157 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2387. Min Range: -1.2387

Max Act: 1.2387. Min Act: -0.0001

Data Index: 1322209 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.2387. Min Range: -1.2387

Max Act: 1.1165. Min Act: -0.0001

Data Index: 752465 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.2387. Min Range: -1.2387

Max Act: 1.1776. Min Act: -0.0001

Data Index: 772417 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.9998. Min Act: -0.0001

Data Index: 897247 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 1.2387. Min Range: -1.2387

Max Act: 1.0475. Min Act: -0.0001

Data Index: 450040 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.9743. Min Act: -0.0001

Data Index: 1236247 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.9685. Min Act: -0.0001

Data Index: 902543 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.9193. Min Act: -0.0001

Data Index: 124963 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.9603. Min Act: -0.0001

Data Index: 519744 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.8874. Min Act: -0.0001

Data Index: 1084082 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.8822. Min Act: -0.0001

Data Index: 836661 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.7399. Min Act: -0.0001

Data Index: 282703 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.9639. Min Act: -0.0001

Data Index: 1291997 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.8723. Min Act: -0.0001

Data Index: 637363 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.9021. Min Act: -0.0001

Data Index: 463172 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.8811. Min Act: -0.0001

Data Index: 435054 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.8551. Min Act: -0.0001

Data Index: 1339283 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.8990. Min Act: -0.0001

Data Index: 1300046 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.8492. Min Act: -0.0001

Data Index: 1177593 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.2387. Min Range: -1.2387

Max Act: 0.8345. Min Act: -0.0001

Data Index: 346653 (C4 (Web Text))

Max Activating Token Index: 466