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

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

Neuron 501 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.6396. Min Act: -0.0000

Data Index: 1000747 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.7014. Min Act: -0.0000

Data Index: 787088 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.5674. Min Act: -0.0000

Data Index: 1062159 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.5598. Min Act: -0.0000

Data Index: 193914 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.5420. Min Act: -0.0000

Data Index: 1313203 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.4621. Min Act: -0.0000

Data Index: 1316241 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.3452. Min Act: -0.0000

Data Index: 487865 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.1880. Min Act: -0.0000

Data Index: 1336987 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.3888. Min Act: -0.0000

Data Index: 495968 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.2167. Min Act: -0.0000

Data Index: 1305707 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.1069. Min Act: -0.0000

Data Index: 82465 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.2024. Min Act: -0.0000

Data Index: 815818 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.1727. Min Act: -0.0000

Data Index: 573238 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.1717. Min Act: -0.0001

Data Index: 731595 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.2755. Min Act: -0.0000

Data Index: 1147175 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.1480. Min Act: -0.0000

Data Index: 1021760 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.2448. Min Act: -0.0000

Data Index: 1157552 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.1345. Min Act: -0.0000

Data Index: 600534 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.2502. Min Act: -0.0000

Data Index: 571267 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 2.7014. Min Range: -2.7014

Max Act: 2.0175. Min Act: -0.0000

Data Index: 449050 (C4 (Web Text))

Max Activating Token Index: 487