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

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

Neuron 1969 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: 1.4355. Min Range: -1.4355

Max Act: 1.3802. Min Act: -0.0000

Data Index: 1613663 (Python Code)

Max Activating Token Index: 598

Text #1

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.4355. Min Act: -0.0000

Data Index: 1423087 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.3863. Min Act: -0.0000

Data Index: 1407778 (Python Code)

Max Activating Token Index: 484

Text #3

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1263775 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1476942 (Python Code)

Max Activating Token Index: 593

Text #5

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1144397 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1630582 (Python Code)

Max Activating Token Index: 467

Text #7

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1380781 (Python Code)

Max Activating Token Index: 945

Text #8

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1516783 (Python Code)

Max Activating Token Index: 612

Text #9

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1415503 (Python Code)

Max Activating Token Index: 468

Text #10

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1606228 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1630519 (Python Code)

Max Activating Token Index: 391

Text #12

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.0795. Min Act: -0.0000

Data Index: 340702 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.0805. Min Act: -0.0000

Data Index: 1644846 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.1034. Min Act: -0.0000

Data Index: 258313 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.0387. Min Act: -0.0000

Data Index: 1452440 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 1.4355. Min Range: -1.4355

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1448174 (Python Code)

Max Activating Token Index: 404

Text #17

Max Range: 1.4355. Min Range: -1.4355

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1120468 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 1.4355. Min Range: -1.4355

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1615932 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 1.4355. Min Range: -1.4355

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1628027 (Python Code)

Max Activating Token Index: 780