Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 71 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0006

Data Index: 484060 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0432. Min Act: -0.0006

Data Index: 374709 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0436. Min Act: -0.0006

Data Index: 794554 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0443. Min Act: -0.0006

Data Index: 231428 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0417. Min Act: -0.0006

Data Index: 1087719 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0422. Min Act: -0.0006

Data Index: 1305914 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0422. Min Act: -0.0006

Data Index: 406367 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0423. Min Act: -0.0006

Data Index: 175692 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0432. Min Act: -0.0006

Data Index: 105258 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0422. Min Act: -0.0006

Data Index: 646908 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0423. Min Act: -0.0006

Data Index: 41438 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0412. Min Act: -0.0006

Data Index: 372663 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1016409 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1266204 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0407. Min Act: -0.0006

Data Index: 1029315 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0415. Min Act: -0.0006

Data Index: 299015 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0416. Min Act: -0.0006

Data Index: 1105755 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0407. Min Act: -0.0006

Data Index: 522370 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0405. Min Act: -0.0006

Data Index: 936055 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0440. Min Act: -0.0006

Data Index: 1097926 (C4 (Web Text))

Max Activating Token Index: 799