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

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

Neuron 5455 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4471. Min Act: -0.0000

Data Index: 42992 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4339. Min Act: -0.0000

Data Index: 928909 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3594. Min Act: -0.0000

Data Index: 31901 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3748. Min Act: -0.0000

Data Index: 670581 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3482. Min Act: -0.0000

Data Index: 477644 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1060834 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3051. Min Act: -0.0000

Data Index: 421181 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2928. Min Act: -0.0000

Data Index: 422819 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3345. Min Act: -0.0000

Data Index: 39756 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1289863 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2945. Min Act: -0.0000

Data Index: 966592 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2554. Min Act: -0.0000

Data Index: 107460 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2717. Min Act: -0.0000

Data Index: 923938 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2750. Min Act: -0.0000

Data Index: 395082 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2725. Min Act: -0.0000

Data Index: 758790 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2454. Min Act: -0.0000

Data Index: 130553 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2629. Min Act: -0.0000

Data Index: 638694 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2529. Min Act: -0.0000

Data Index: 383913 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2390. Min Act: -0.0000

Data Index: 310502 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.2559. Min Act: -0.0000

Data Index: 791548 (C4 (Web Text))

Max Activating Token Index: 704