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

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

Neuron 3608 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4830. Min Act: -0.0000

Data Index: 1422180 (Python Code)

Max Activating Token Index: 664

Text #1

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3673. Min Act: -0.0000

Data Index: 699315 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2125. Min Act: -0.0000

Data Index: 276382 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1197335 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1537. Min Act: -0.0000

Data Index: 991867 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1715. Min Act: -0.0000

Data Index: 538131 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1424. Min Act: -0.0000

Data Index: 732083 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1140. Min Act: -0.0000

Data Index: 265847 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1237. Min Act: -0.0000

Data Index: 148556 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1477. Min Act: -0.0000

Data Index: 1092241 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.0753. Min Act: -0.0000

Data Index: 796313 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1008. Min Act: -0.0000

Data Index: 177260 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.0525. Min Act: -0.0000

Data Index: 310517 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.0966. Min Act: -0.0000

Data Index: 333014 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.0827. Min Act: -0.0000

Data Index: 92932 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.0465. Min Act: -0.0000

Data Index: 259701 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1073. Min Act: -0.0000

Data Index: 844279 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1491845 (Python Code)

Max Activating Token Index: 353

Text #18

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.0689. Min Act: -0.0000

Data Index: 625052 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1350236 (C4 (Web Text))

Max Activating Token Index: 5