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

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

Neuron 1249 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.5413. Min Act: -0.0004

Data Index: 891330 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.5415. Min Act: -0.0004

Data Index: 189820 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.4229. Min Act: -0.0004

Data Index: 873944 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.4996. Min Act: -0.0004

Data Index: 919335 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.5231. Min Act: -0.0004

Data Index: 884446 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.4890. Min Act: -0.0004

Data Index: 774027 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.5143. Min Act: -0.0004

Data Index: 1267853 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.4781. Min Act: -0.0004

Data Index: 729865 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.4218. Min Act: -0.0004

Data Index: 17906 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.5651. Min Act: -0.0004

Data Index: 742728 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.4426. Min Act: -0.0004

Data Index: 1215606 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.2887. Min Act: -0.0004

Data Index: 1317505 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.3355. Min Act: -0.0004

Data Index: 717266 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.3730. Min Act: -0.0004

Data Index: 1203495 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.2977. Min Act: -0.0004

Data Index: 794347 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.3990. Min Act: -0.0004

Data Index: 969249 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.4229. Min Act: -0.0004

Data Index: 1094556 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.3460. Min Act: -0.0004

Data Index: 555193 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.3737. Min Act: -0.0004

Data Index: 200024 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.4794. Min Act: -0.0004

Data Index: 1245073 (C4 (Web Text))

Max Activating Token Index: 693