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

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

Neuron 15 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.1462. Min Range: -2.1462

Max Act: 2.1462. Min Act: -0.0002

Data Index: 472570 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 2.1462. Min Range: -2.1462

Max Act: 2.1238. Min Act: -0.0002

Data Index: 709912 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.9850. Min Act: -0.0002

Data Index: 884780 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.9959. Min Act: -0.0002

Data Index: 681775 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.9282. Min Act: -0.0002

Data Index: 219631 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.9014. Min Act: -0.0002

Data Index: 1327538 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8623. Min Act: -0.0002

Data Index: 1096418 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8515. Min Act: -0.0002

Data Index: 893962 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8967. Min Act: -0.0002

Data Index: 2177 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.9345. Min Act: -0.0002

Data Index: 27220 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8484. Min Act: -0.0002

Data Index: 611512 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8641. Min Act: -0.0002

Data Index: 1177413 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.9098. Min Act: -0.0002

Data Index: 110569 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8881. Min Act: -0.0002

Data Index: 198441 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8499. Min Act: -0.0003

Data Index: 1336391 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8029. Min Act: -0.0002

Data Index: 23613 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8979. Min Act: -0.0002

Data Index: 891786 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8667. Min Act: -0.0002

Data Index: 111488 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8444. Min Act: -0.0002

Data Index: 456203 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 2.1462. Min Range: -2.1462

Max Act: 1.8429. Min Act: -0.0002

Data Index: 911629 (C4 (Web Text))

Max Activating Token Index: 464