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

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

Neuron 904 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.7387. Min Act: -0.0000

Data Index: 1118233 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.5114. Min Act: -0.0000

Data Index: 908821 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.4906. Min Act: -0.0000

Data Index: 279208 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.3507. Min Act: -0.0000

Data Index: 108407 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.1383. Min Act: -0.0000

Data Index: 1306620 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.1403. Min Act: -0.0000

Data Index: 714516 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.0312. Min Act: -0.0000

Data Index: 944716 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.1170. Min Act: -0.0000

Data Index: 1013622 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.1059. Min Act: -0.0000

Data Index: 627187 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.0745. Min Act: -0.0000

Data Index: 244828 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.1794. Min Act: -0.0000

Data Index: 902432 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.0270. Min Act: -0.0000

Data Index: 104617 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.9055. Min Act: -0.0000

Data Index: 456062 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.0064. Min Act: -0.0000

Data Index: 1225829 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.9944. Min Act: -0.0000

Data Index: 347745 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.9906. Min Act: -0.0000

Data Index: 26636 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.9923. Min Act: -0.0000

Data Index: 265752 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.0729. Min Act: -0.0000

Data Index: 1358801 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.0800. Min Act: -0.0000

Data Index: 198720 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.8560. Min Act: -0.0000

Data Index: 148202 (C4 (Web Text))

Max Activating Token Index: 996