Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 726 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.3285. Min Act: -0.0005

Data Index: 22614 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2895. Min Act: -0.0005

Data Index: 492682 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2887. Min Act: -0.0005

Data Index: 1193272 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2719. Min Act: -0.0005

Data Index: 190919 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2651. Min Act: -0.0005

Data Index: 1163762 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2572. Min Act: -0.0005

Data Index: 187160 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2822. Min Act: -0.0005

Data Index: 852348 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2367. Min Act: -0.0005

Data Index: 1164593 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2600. Min Act: -0.0005

Data Index: 1177071 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2333. Min Act: -0.0005

Data Index: 648924 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2516. Min Act: -0.0005

Data Index: 775227 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2311. Min Act: -0.0005

Data Index: 335180 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2383. Min Act: -0.0005

Data Index: 239040 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2383. Min Act: -0.0005

Data Index: 583886 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2373. Min Act: -0.0005

Data Index: 1187148 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2434. Min Act: -0.0005

Data Index: 91830 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2338. Min Act: -0.0005

Data Index: 210794 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2337. Min Act: -0.0005

Data Index: 178431 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2240. Min Act: -0.0005

Data Index: 1172865 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2146. Min Act: -0.0005

Data Index: 937294 (C4 (Web Text))

Max Activating Token Index: 414