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

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

Neuron 748 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.7037. Min Act: -0.0002

Data Index: 342051 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.7267. Min Act: -0.0002

Data Index: 142743 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6404. Min Act: -0.0002

Data Index: 1255785 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6025. Min Act: -0.0002

Data Index: 52522 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6307. Min Act: -0.0002

Data Index: 1089507 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6089. Min Act: -0.0002

Data Index: 970336 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6113. Min Act: -0.0002

Data Index: 540643 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5517. Min Act: -0.0002

Data Index: 475006 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6153. Min Act: -0.0002

Data Index: 255463 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5757. Min Act: -0.0002

Data Index: 481853 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6113. Min Act: -0.0002

Data Index: 782421 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5753. Min Act: -0.0002

Data Index: 284179 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5977. Min Act: -0.0002

Data Index: 674839 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5583. Min Act: -0.0002

Data Index: 256764 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5448. Min Act: -0.0002

Data Index: 841201 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5562. Min Act: -0.0002

Data Index: 530119 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5557. Min Act: -0.0002

Data Index: 103955 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5712. Min Act: -0.0002

Data Index: 382225 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5658. Min Act: -0.0002

Data Index: 771422 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5278. Min Act: -0.0002

Data Index: 910252 (C4 (Web Text))

Max Activating Token Index: 368