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

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

Neuron 5638 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: 0.2970. Min Range: -0.2970

Max Act: 0.2933. Min Act: -0.0002

Data Index: 997741 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2970. Min Act: -0.0002

Data Index: 916872 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2731. Min Act: -0.0002

Data Index: 1027581 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2688. Min Act: -0.0002

Data Index: 537412 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2721. Min Act: -0.0002

Data Index: 263705 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2719. Min Act: -0.0002

Data Index: 69530 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2683. Min Act: -0.0002

Data Index: 278966 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2747. Min Act: -0.0002

Data Index: 239830 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2593. Min Act: -0.0002

Data Index: 486019 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2636. Min Act: -0.0002

Data Index: 1143269 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2537. Min Act: -0.0002

Data Index: 1326640 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2505. Min Act: -0.0002

Data Index: 521781 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2522. Min Act: -0.0002

Data Index: 580637 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2436. Min Act: -0.0002

Data Index: 62612 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2497. Min Act: -0.0002

Data Index: 955630 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2461. Min Act: -0.0002

Data Index: 445344 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2478. Min Act: -0.0002

Data Index: 586767 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2401. Min Act: -0.0003

Data Index: 439239 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2419. Min Act: -0.0002

Data Index: 1025479 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2386. Min Act: -0.0002

Data Index: 455199 (C4 (Web Text))

Max Activating Token Index: 547