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

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

Neuron 4227 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: 0.8852. Min Range: -0.8852

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1262193 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.8170. Min Act: -0.0000

Data Index: 22710 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.8852. Min Act: -0.0000

Data Index: 439286 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.8258. Min Act: -0.0001

Data Index: 792888 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.7917. Min Act: -0.0000

Data Index: 515776 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1352536 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.7934. Min Act: -0.0000

Data Index: 855194 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.7724. Min Act: -0.0000

Data Index: 764680 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.7338. Min Act: -0.0000

Data Index: 591927 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.6130. Min Act: -0.0000

Data Index: 667474 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.7314. Min Act: -0.0001

Data Index: 345847 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1168432 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.6688. Min Act: -0.0000

Data Index: 710744 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.6328. Min Act: -0.0001

Data Index: 215358 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1315329 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.5937. Min Act: -0.0000

Data Index: 88915 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.6206. Min Act: -0.0001

Data Index: 1284377 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.6079. Min Act: -0.0000

Data Index: 444835 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.5379. Min Act: -0.0000

Data Index: 697993 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.8852. Min Range: -0.8852

Max Act: 0.5654. Min Act: -0.0000

Data Index: 665141 (C4 (Web Text))

Max Activating Token Index: 102