Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3324 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.5346. Min Act: -0.0000

Data Index: 758976 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.4350. Min Act: -0.0000

Data Index: 1030120 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.5728. Min Act: -0.0000

Data Index: 491021 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.3401. Min Act: -0.0000

Data Index: 294258 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.3795. Min Act: -0.0000

Data Index: 1026678 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.3674. Min Act: -0.0000

Data Index: 474277 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.3297. Min Act: -0.0000

Data Index: 142977 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.2758. Min Act: -0.0000

Data Index: 193609 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.3322. Min Act: -0.0000

Data Index: 970591 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.3057. Min Act: -0.0000

Data Index: 871530 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.2274. Min Act: -0.0000

Data Index: 482241 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.2292. Min Act: -0.0000

Data Index: 875943 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.2962. Min Act: -0.0000

Data Index: 315751 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1180656 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.2578. Min Act: -0.0000

Data Index: 944560 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.1486. Min Act: -0.0000

Data Index: 767850 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.1748. Min Act: -0.0000

Data Index: 49700 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.0723. Min Act: -0.0000

Data Index: 346519 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.2102. Min Act: -0.0000

Data Index: 352519 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.5728. Min Range: -1.5728

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1118429 (C4 (Web Text))

Max Activating Token Index: 290