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

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

Neuron 3693 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.5362. Min Act: -0.0000

Data Index: 927546 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.4839. Min Act: -0.0000

Data Index: 700958 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.4002. Min Act: -0.0000

Data Index: 534758 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.4270. Min Act: -0.0000

Data Index: 379698 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.3221. Min Act: -0.0000

Data Index: 558591 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1024368 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.3532. Min Act: -0.0000

Data Index: 555975 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.3491. Min Act: -0.0000

Data Index: 926093 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.1856. Min Act: -0.0000

Data Index: 939609 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.3188. Min Act: -0.0000

Data Index: 904275 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.3147. Min Act: -0.0000

Data Index: 679968 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2974. Min Act: -0.0000

Data Index: 1061990 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2891. Min Act: -0.0000

Data Index: 929716 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1203653 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2856. Min Act: -0.0000

Data Index: 166516 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1023139 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2505. Min Act: -0.0000

Data Index: 1286449 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1037843 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.2170. Min Act: -0.0000

Data Index: 270480 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 1.5362. Min Range: -1.5362

Max Act: 1.1412. Min Act: -0.0000

Data Index: 940940 (C4 (Web Text))

Max Activating Token Index: 922