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

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

Neuron 2065 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.5437. Min Act: -0.0000

Data Index: 1034564 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.6756. Min Act: -0.0000

Data Index: 558735 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.4982. Min Act: -0.0000

Data Index: 783619 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.3616. Min Act: -0.0000

Data Index: 473166 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1163994 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2789. Min Act: -0.0000

Data Index: 700781 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1230322 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.3484. Min Act: -0.0000

Data Index: 224656 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.3474. Min Act: -0.0000

Data Index: 1234600 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.4096. Min Act: -0.0000

Data Index: 763420 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.3188. Min Act: -0.0000

Data Index: 373568 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2373. Min Act: -0.0000

Data Index: 799364 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2277. Min Act: -0.0000

Data Index: 255199 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1079061 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2056. Min Act: -0.0000

Data Index: 153414 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2231. Min Act: -0.0000

Data Index: 144174 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.1896. Min Act: -0.0000

Data Index: 519728 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.2015. Min Act: -0.0000

Data Index: 262277 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1029879 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 1.6756. Min Range: -1.6756

Max Act: 1.1679. Min Act: -0.0000

Data Index: 613485 (C4 (Web Text))

Max Activating Token Index: 60