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

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

Neuron 510 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: 0.3283. Min Range: -0.3283

Max Act: 0.3283. Min Act: -0.0001

Data Index: 324067 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3105. Min Act: -0.0001

Data Index: 14361 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2952. Min Act: -0.0001

Data Index: 390573 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2924. Min Act: -0.0001

Data Index: 1083308 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2859. Min Act: -0.0001

Data Index: 386288 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2709. Min Act: -0.0001

Data Index: 834841 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2781. Min Act: -0.0001

Data Index: 1186662 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2513. Min Act: -0.0001

Data Index: 959031 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2745. Min Act: -0.0001

Data Index: 1190684 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2453. Min Act: -0.0001

Data Index: 167856 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2619. Min Act: -0.0001

Data Index: 601626 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2708. Min Act: -0.0001

Data Index: 754686 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2549. Min Act: -0.0001

Data Index: 602697 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2740. Min Act: -0.0001

Data Index: 655758 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2731. Min Act: -0.0001

Data Index: 584562 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2799. Min Act: -0.0001

Data Index: 1254024 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2680. Min Act: -0.0001

Data Index: 760707 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2652. Min Act: -0.0001

Data Index: 200695 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2558. Min Act: -0.0001

Data Index: 1115518 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.2455. Min Act: -0.0001

Data Index: 461323 (C4 (Web Text))

Max Activating Token Index: 226