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

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

Neuron 5988 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0850. Min Act: -0.0000

Data Index: 538837 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.3854. Min Act: -0.0000

Data Index: 862207 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.9072. Min Act: -0.0000

Data Index: 850299 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.0519. Min Act: -0.0000

Data Index: 860425 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.1190. Min Act: -0.0000

Data Index: 759802 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.2275. Min Act: -0.0000

Data Index: 275564 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.4608. Min Act: -0.0000

Data Index: 573630 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.4417. Min Act: -0.0000

Data Index: 427752 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.1780. Min Act: -0.0000

Data Index: 1079934 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.2244. Min Act: -0.0000

Data Index: 437783 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 4.0850. Min Range: -4.0850

Max Act: 1.8543. Min Act: -0.0000

Data Index: 965303 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.0455. Min Act: -0.0000

Data Index: 1354921 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 4.0850. Min Range: -4.0850

Max Act: 1.8028. Min Act: -0.0000

Data Index: 1233701 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 4.0850. Min Range: -4.0850

Max Act: 1.8644. Min Act: -0.0000

Data Index: 569386 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.0578. Min Act: -0.0000

Data Index: 575459 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.0513. Min Act: -0.0000

Data Index: 324163 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 4.0850. Min Range: -4.0850

Max Act: 1.8509. Min Act: -0.0000

Data Index: 1326845 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 4.0850. Min Range: -4.0850

Max Act: 2.0266. Min Act: -0.0000

Data Index: 262474 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 4.0850. Min Range: -4.0850

Max Act: 1.8272. Min Act: -0.0000

Data Index: 250240 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 4.0850. Min Range: -4.0850

Max Act: 1.8014. Min Act: -0.0000

Data Index: 287576 (C4 (Web Text))

Max Activating Token Index: 835