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

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

Neuron 4744 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1199435 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.7739. Min Act: -0.0000

Data Index: 463926 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1169570 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.6795. Min Act: -0.0000

Data Index: 638006 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.6947. Min Act: -0.0000

Data Index: 101382 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.6049. Min Act: -0.0000

Data Index: 78507 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.6344. Min Act: -0.0000

Data Index: 446225 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1225327 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.5661. Min Act: -0.0000

Data Index: 961904 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.5884. Min Act: -0.0000

Data Index: 206225 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.5495. Min Act: -0.0000

Data Index: 33774 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.5468. Min Act: -0.0000

Data Index: 661278 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.5354. Min Act: -0.0000

Data Index: 42110 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1328983 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.5296. Min Act: -0.0000

Data Index: 158985 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.5191. Min Act: -0.0000

Data Index: 435700 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.4843. Min Act: -0.0000

Data Index: 600213 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.5135. Min Act: -0.0000

Data Index: 51780 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.4911. Min Act: -0.0000

Data Index: 408438 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.9770. Min Range: -0.9770

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1003688 (C4 (Web Text))

Max Activating Token Index: 664