Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 690 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.3111. Min Act: -0.0001

Data Index: 1153529 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.3487. Min Act: -0.0001

Data Index: 381754 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2779. Min Act: -0.0001

Data Index: 926545 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.3097. Min Act: -0.0001

Data Index: 968769 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2944. Min Act: -0.0001

Data Index: 1008924 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2892. Min Act: -0.0001

Data Index: 547379 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2897. Min Act: -0.0001

Data Index: 750607 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2764. Min Act: -0.0001

Data Index: 1319186 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2656. Min Act: -0.0000

Data Index: 81073 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2840. Min Act: -0.0001

Data Index: 956953 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2770. Min Act: -0.0001

Data Index: 340867 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2746. Min Act: -0.0001

Data Index: 1058107 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2511. Min Act: -0.0001

Data Index: 180309 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2586. Min Act: -0.0001

Data Index: 967937 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2712. Min Act: -0.0001

Data Index: 627221 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2584. Min Act: -0.0000

Data Index: 563795 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2929. Min Act: -0.0001

Data Index: 798953 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2563. Min Act: -0.0001

Data Index: 847781 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2613. Min Act: -0.0001

Data Index: 31133 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.3487. Min Range: -0.3487

Max Act: 0.2605. Min Act: -0.0001

Data Index: 97737 (C4 (Web Text))

Max Activating Token Index: 892