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

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

Neuron 5608 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2722. Min Range: -3.2722

Max Act: 3.2722. Min Act: -0.0000

Data Index: 1134499 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.9848. Min Act: -0.0000

Data Index: 805172 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.8761. Min Act: -0.0000

Data Index: 910519 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.5654. Min Act: -0.0000

Data Index: 621386 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.9336. Min Act: -0.0000

Data Index: 541733 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.6400. Min Act: -0.0000

Data Index: 434344 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.5832. Min Act: -0.0000

Data Index: 517324 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.5463. Min Act: -0.0000

Data Index: 1095290 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.6981. Min Act: -0.0000

Data Index: 578207 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.3705. Min Act: -0.0000

Data Index: 290032 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.4885. Min Act: -0.0000

Data Index: 104697 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.4603. Min Act: -0.0000

Data Index: 1193167 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.3234. Min Act: -0.0000

Data Index: 1241265 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.4610. Min Act: -0.0000

Data Index: 128225 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.5911. Min Act: -0.0000

Data Index: 280021 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.4079. Min Act: -0.0000

Data Index: 1127429 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.2633. Min Act: -0.0000

Data Index: 1239991 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.3730. Min Act: -0.0000

Data Index: 166310 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.3666. Min Act: -0.0000

Data Index: 1323406 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 3.2722. Min Range: -3.2722

Max Act: 2.3576. Min Act: -0.0000

Data Index: 607877 (C4 (Web Text))

Max Activating Token Index: 906