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

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

Neuron 4730 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: 0.5282. Min Range: -0.5282

Max Act: 0.5282. Min Act: -0.0002

Data Index: 1181756 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4895. Min Act: -0.0002

Data Index: 715788 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4740. Min Act: -0.0002

Data Index: 44457 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4706. Min Act: -0.0002

Data Index: 1313518 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4678. Min Act: -0.0002

Data Index: 1303516 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4713. Min Act: -0.0002

Data Index: 443362 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4561. Min Act: -0.0002

Data Index: 462049 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4452. Min Act: -0.0002

Data Index: 1055967 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4370. Min Act: -0.0002

Data Index: 1103023 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4287. Min Act: -0.0002

Data Index: 698417 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4333. Min Act: -0.0002

Data Index: 823690 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4322. Min Act: -0.0002

Data Index: 93672 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4301. Min Act: -0.0002

Data Index: 406610 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4316. Min Act: -0.0002

Data Index: 543573 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4326. Min Act: -0.0002

Data Index: 1160856 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4367. Min Act: -0.0002

Data Index: 465867 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4224. Min Act: -0.0002

Data Index: 905582 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4130. Min Act: -0.0002

Data Index: 829465 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4178. Min Act: -0.0002

Data Index: 630371 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4048. Min Act: -0.0003

Data Index: 780897 (C4 (Web Text))

Max Activating Token Index: 474