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

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

Neuron 4151 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: 0.0614. Min Range: -0.0614

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1036985 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0581. Min Act: -0.0002

Data Index: 482569 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0558. Min Act: -0.0002

Data Index: 201896 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0570. Min Act: -0.0002

Data Index: 111184 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1368160 (Python Code)

Max Activating Token Index: 794

Text #5

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0523. Min Act: -0.0002

Data Index: 870827 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0537. Min Act: -0.0002

Data Index: 444309 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1335139 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0513. Min Act: -0.0002

Data Index: 440223 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1317677 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0493. Min Act: -0.0002

Data Index: 913406 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1488682 (Python Code)

Max Activating Token Index: 635

Text #12

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0497. Min Act: -0.0002

Data Index: 603864 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1390832 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1550351 (Python Code)

Max Activating Token Index: 985

Text #15

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1253755 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1050824 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0454. Min Act: -0.0002

Data Index: 811087 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1537867 (Python Code)

Max Activating Token Index: 944

Text #19

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0444. Min Act: -0.0002

Data Index: 651076 (C4 (Web Text))

Max Activating Token Index: 1008