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

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

Neuron 2805 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.3697. Min Act: -0.0000

Data Index: 97182 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.2017. Min Act: -0.0000

Data Index: 640712 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1053880 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.2374. Min Act: -0.0001

Data Index: 1490717 (Python Code)

Max Activating Token Index: 452

Text #4

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.1435. Min Act: -0.0000

Data Index: 1527473 (Python Code)

Max Activating Token Index: 1013

Text #5

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0701. Min Act: -0.0000

Data Index: 399960 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0586. Min Act: -0.0000

Data Index: 806962 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0126. Min Act: -0.0000

Data Index: 838885 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0430. Min Act: -0.0000

Data Index: 682897 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9848. Min Act: -0.0000

Data Index: 578538 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1215633 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1399220 (Python Code)

Max Activating Token Index: 934

Text #12

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1093345 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9102. Min Act: -0.0000

Data Index: 590629 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9464. Min Act: -0.0000

Data Index: 363423 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1238232 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1103801 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1394626 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1188170 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1544373 (Python Code)

Max Activating Token Index: 873