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

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

Neuron 608 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3863. Min Range: -1.3863

Max Act: 1.3863. Min Act: -0.0000

Data Index: 1333031 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 1.3863. Min Range: -1.3863

Max Act: 1.1392. Min Act: -0.0000

Data Index: 1300156 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 1.3863. Min Range: -1.3863

Max Act: 1.2298. Min Act: -0.0000

Data Index: 299017 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.3863. Min Range: -1.3863

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1395980 (Python Code)

Max Activating Token Index: 908

Text #4

Max Range: 1.3863. Min Range: -1.3863

Max Act: 1.0481. Min Act: -0.0000

Data Index: 862804 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.9021. Min Act: -0.0000

Data Index: 290309 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1217549 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.3863. Min Range: -1.3863

Max Act: 1.0099. Min Act: -0.0000

Data Index: 671463 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.9061. Min Act: -0.0000

Data Index: 837504 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1009630 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.8352. Min Act: -0.0000

Data Index: 432083 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1454418 (Python Code)

Max Activating Token Index: 229

Text #12

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.6920. Min Act: -0.0000

Data Index: 752526 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1576051 (Python Code)

Max Activating Token Index: 383

Text #14

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.7080. Min Act: -0.0000

Data Index: 40233 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.6340. Min Act: -0.0000

Data Index: 46378 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1376491 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.6905. Min Act: -0.0000

Data Index: 371272 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1295272 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.3863. Min Range: -1.3863

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1471511 (Python Code)

Max Activating Token Index: 282