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

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

Neuron 4788 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.4393. Min Act: -0.0000

Data Index: 979293 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.4479. Min Act: -0.0000

Data Index: 1166243 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.1666. Min Act: -0.0000

Data Index: 274142 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.0235. Min Act: -0.0000

Data Index: 58162 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1325934 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9197. Min Act: -0.0000

Data Index: 351450 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9782. Min Act: -0.0000

Data Index: 768153 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.7777. Min Act: -0.0000

Data Index: 342433 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.8864. Min Act: -0.0000

Data Index: 110618 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9770. Min Act: -0.0000

Data Index: 116952 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9721. Min Act: -0.0000

Data Index: 867681 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.8914. Min Act: -0.0000

Data Index: 774638 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9326. Min Act: -0.0000

Data Index: 696821 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.8793. Min Act: -0.0000

Data Index: 681946 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.8417. Min Act: -0.0001

Data Index: 19324 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.8852. Min Act: -0.0000

Data Index: 155370 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1297735 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1077017 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.8755. Min Act: -0.0000

Data Index: 323500 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1022759 (C4 (Web Text))

Max Activating Token Index: 41