Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1608 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.8872. Min Act: -0.0000

Data Index: 1246825 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 8.0364. Min Range: -8.0364

Max Act: 8.0153. Min Act: -0.0000

Data Index: 539781 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 8.0364. Min Range: -8.0364

Max Act: 8.0100. Min Act: -0.0000

Data Index: 5944 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.9725. Min Act: -0.0000

Data Index: 1292582 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.8933. Min Act: -0.0000

Data Index: 604035 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.8818. Min Act: -0.0000

Data Index: 1143196 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.7106. Min Act: -0.0000

Data Index: 760464 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 8.0364. Min Range: -8.0364

Max Act: 8.0364. Min Act: -0.0000

Data Index: 683754 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.8703. Min Act: -0.0000

Data Index: 41870 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 8.0364. Min Range: -8.0364

Max Act: 8.0202. Min Act: -0.0000

Data Index: 1256649 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.6639. Min Act: -0.0000

Data Index: 1034608 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.8766. Min Act: -0.0000

Data Index: 924368 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.7007. Min Act: -0.0000

Data Index: 1208566 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.6694. Min Act: -0.0000

Data Index: 1290248 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.8431. Min Act: -0.0000

Data Index: 1298426 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.8540. Min Act: -0.0000

Data Index: 474979 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.7336. Min Act: -0.0000

Data Index: 1144318 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.7267. Min Act: -0.0000

Data Index: 182107 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.7025. Min Act: -0.0000

Data Index: 849236 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 8.0364. Min Range: -8.0364

Max Act: 7.7245. Min Act: -0.0000

Data Index: 1067000 (C4 (Web Text))

Max Activating Token Index: 408