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

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

Neuron 1942 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: 0.3540. Min Range: -0.3540

Max Act: 0.3540. Min Act: -0.0001

Data Index: 100752 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.3332. Min Act: -0.0001

Data Index: 502446 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.3175. Min Act: -0.0001

Data Index: 910283 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2716. Min Act: -0.0001

Data Index: 872589 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2794. Min Act: -0.0001

Data Index: 1052180 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2819. Min Act: -0.0001

Data Index: 724513 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1353711 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2811. Min Act: -0.0001

Data Index: 1299752 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2755. Min Act: -0.0001

Data Index: 260120 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2671. Min Act: -0.0001

Data Index: 637526 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2560. Min Act: -0.0001

Data Index: 9049 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2575. Min Act: -0.0001

Data Index: 1009944 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2582. Min Act: -0.0001

Data Index: 156611 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2604. Min Act: -0.0001

Data Index: 1534579 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2513. Min Act: -0.0001

Data Index: 755489 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2515. Min Act: -0.0001

Data Index: 219815 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2372. Min Act: -0.0001

Data Index: 162913 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2603. Min Act: -0.0001

Data Index: 389582 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2449. Min Act: -0.0001

Data Index: 734835 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2489. Min Act: -0.0001

Data Index: 299589 (C4 (Web Text))

Max Activating Token Index: 410