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

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

Neuron 4598 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: 4.2196. Min Range: -4.2196

Max Act: 4.2196. Min Act: -0.0000

Data Index: 105791 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.9948. Min Act: -0.0000

Data Index: 313514 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 4.2196. Min Range: -4.2196

Max Act: 4.1020. Min Act: -0.0000

Data Index: 1193093 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 4.2196. Min Range: -4.2196

Max Act: 4.0416. Min Act: -0.0000

Data Index: 1003487 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.6062. Min Act: -0.0000

Data Index: 394083 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.7347. Min Act: -0.0000

Data Index: 514404 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.6764. Min Act: -0.0000

Data Index: 674423 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.6875. Min Act: -0.0000

Data Index: 406131 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.6391. Min Act: -0.0000

Data Index: 69833 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.4312. Min Act: -0.0000

Data Index: 1306767 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.4071. Min Act: -0.0000

Data Index: 331887 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.5427. Min Act: -0.0000

Data Index: 91564 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.4086. Min Act: -0.0000

Data Index: 320881 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.5185. Min Act: -0.0000

Data Index: 1175984 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.3537. Min Act: -0.0000

Data Index: 833507 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.4961. Min Act: -0.0000

Data Index: 1177614 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.4914. Min Act: -0.0000

Data Index: 893844 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.4624. Min Act: -0.0000

Data Index: 868774 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.4199. Min Act: -0.0000

Data Index: 507524 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 4.2196. Min Range: -4.2196

Max Act: 3.4452. Min Act: -0.0000

Data Index: 823929 (C4 (Web Text))

Max Activating Token Index: 323