Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 702 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.4090. Min Act: -0.0001

Data Index: 1335018 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3803. Min Act: -0.0001

Data Index: 228325 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3914. Min Act: -0.0001

Data Index: 579373 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3847. Min Act: -0.0001

Data Index: 1008952 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3600. Min Act: -0.0001

Data Index: 370169 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3602. Min Act: -0.0001

Data Index: 193571 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3537. Min Act: -0.0001

Data Index: 1201842 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3497. Min Act: -0.0001

Data Index: 777405 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3493. Min Act: -0.0001

Data Index: 301085 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3568. Min Act: -0.0001

Data Index: 987973 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3541. Min Act: -0.0001

Data Index: 642763 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3550. Min Act: -0.0001

Data Index: 294911 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3504. Min Act: -0.0001

Data Index: 591060 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3396. Min Act: -0.0001

Data Index: 1111304 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3592. Min Act: -0.0001

Data Index: 57750 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3461. Min Act: -0.0001

Data Index: 716672 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3428. Min Act: -0.0001

Data Index: 578562 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3517. Min Act: -0.0001

Data Index: 700943 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3328. Min Act: -0.0001

Data Index: 766068 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3321. Min Act: -0.0001

Data Index: 474983 (C4 (Web Text))

Max Activating Token Index: 845