Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1650 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0822. Min Act: -0.0003

Data Index: 188598 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0794. Min Act: -0.0003

Data Index: 522695 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1095092 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0556. Min Act: -0.0003

Data Index: 286862 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1495911 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0554. Min Act: -0.0003

Data Index: 242297 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0559. Min Act: -0.0003

Data Index: 498553 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0540. Min Act: -0.0003

Data Index: 56014 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1495314 (Python Code)

Max Activating Token Index: 1003

Text #9

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0517. Min Act: -0.0003

Data Index: 443091 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1029716 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0535. Min Act: -0.0003

Data Index: 478094 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0524. Min Act: -0.0003

Data Index: 426721 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0515. Min Act: -0.0003

Data Index: 725019 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0504. Min Act: -0.0003

Data Index: 427515 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0502. Min Act: -0.0004

Data Index: 1192251 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0511. Min Act: -0.0003

Data Index: 941627 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0501. Min Act: -0.0004

Data Index: 1161406 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0497. Min Act: -0.0003

Data Index: 713815 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0498. Min Act: -0.0003

Data Index: 434413 (C4 (Web Text))

Max Activating Token Index: 275