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

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

Neuron 4715 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1006838 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1332723 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3131. Min Act: -0.0000

Data Index: 547746 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1347947 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3706. Min Act: -0.0000

Data Index: 157871 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2934. Min Act: -0.0000

Data Index: 94930 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2800. Min Act: -0.0000

Data Index: 826878 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2743. Min Act: -0.0000

Data Index: 978750 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2667. Min Act: -0.0000

Data Index: 146435 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2988. Min Act: -0.0000

Data Index: 383804 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2559. Min Act: -0.0000

Data Index: 630171 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2575. Min Act: -0.0000

Data Index: 340937 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2689. Min Act: -0.0000

Data Index: 470697 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2491. Min Act: -0.0000

Data Index: 156488 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2355. Min Act: -0.0000

Data Index: 544333 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2265. Min Act: -0.0000

Data Index: 157889 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1260267 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.1954. Min Act: -0.0000

Data Index: 461970 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2054. Min Act: -0.0000

Data Index: 718029 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.1895. Min Act: -0.0000

Data Index: 930302 (C4 (Web Text))

Max Activating Token Index: 858