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

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

Neuron 4461 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1569739 (Python Code)

Max Activating Token Index: 563

Text #1

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7271. Min Act: 0.0001

Data Index: 1281658 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7026. Min Act: 0.0000

Data Index: 426512 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1422728 (Python Code)

Max Activating Token Index: 600

Text #4

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7121. Min Act: -0.0000

Data Index: 433759 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6840. Min Act: 0.0001

Data Index: 143311 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6774. Min Act: 0.0000

Data Index: 424328 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6498. Min Act: -0.0000

Data Index: 970072 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6672. Min Act: 0.0001

Data Index: 1320928 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6836. Min Act: 0.0001

Data Index: 784351 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6506. Min Act: -0.0000

Data Index: 802927 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6732. Min Act: 0.0000

Data Index: 610988 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6214. Min Act: 0.0000

Data Index: 421697 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6394. Min Act: -0.0000

Data Index: 9834 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6212. Min Act: -0.0000

Data Index: 893678 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5745. Min Act: -0.0000

Data Index: 423311 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5574. Min Act: 0.0001

Data Index: 219466 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5712. Min Act: 0.0000

Data Index: 1105570 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5738. Min Act: 0.0000

Data Index: 1069841 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5460. Min Act: -0.0000

Data Index: 648739 (C4 (Web Text))

Max Activating Token Index: 831