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

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

Neuron 1082 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0001

Data Index: 477002 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1094926 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0653. Min Act: -0.0001

Data Index: 344888 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0598. Min Act: -0.0001

Data Index: 637165 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0595. Min Act: -0.0001

Data Index: 64929 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0621. Min Act: -0.0001

Data Index: 1092000 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1243208 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0611. Min Act: -0.0002

Data Index: 535942 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0523. Min Act: -0.0001

Data Index: 956106 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0567. Min Act: -0.0002

Data Index: 117904 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0519. Min Act: -0.0001

Data Index: 198437 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0525. Min Act: -0.0001

Data Index: 81265 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0555. Min Act: -0.0002

Data Index: 211884 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0562. Min Act: -0.0001

Data Index: 226201 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0544. Min Act: -0.0002

Data Index: 559623 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1304980 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0493. Min Act: -0.0001

Data Index: 121975 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0596. Min Act: -0.0001

Data Index: 455782 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0628. Min Act: -0.0002

Data Index: 153808 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0577. Min Act: -0.0001

Data Index: 375377 (C4 (Web Text))

Max Activating Token Index: 590