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

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

Neuron 4338 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.9480. Min Act: -0.0000

Data Index: 235010 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1103664 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1263379 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.6495. Min Act: -0.0000

Data Index: 79323 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.6181. Min Act: -0.0000

Data Index: 972469 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1006481 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1027922 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.5592. Min Act: -0.0000

Data Index: 630286 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.5397. Min Act: -0.0000

Data Index: 309311 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.5484. Min Act: -0.0000

Data Index: 424146 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1239543 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.4911. Min Act: -0.0000

Data Index: 909629 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.4914. Min Act: -0.0000

Data Index: 186952 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.5163. Min Act: -0.0000

Data Index: 205870 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.5074. Min Act: -0.0000

Data Index: 914349 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.5020. Min Act: -0.0000

Data Index: 675955 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.5307. Min Act: -0.0000

Data Index: 962355 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1270906 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.4864. Min Act: -0.0000

Data Index: 575874 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.4817. Min Act: -0.0000

Data Index: 33650 (C4 (Web Text))

Max Activating Token Index: 783