Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 96 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7697. Min Act: -0.0000

Data Index: 520387 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7312. Min Act: -0.0001

Data Index: 1277293 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7021. Min Act: -0.0000

Data Index: 880205 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6392. Min Act: -0.0001

Data Index: 773671 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5285. Min Act: -0.0000

Data Index: 590341 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5632. Min Act: -0.0001

Data Index: 704788 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5604. Min Act: -0.0000

Data Index: 504747 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6345. Min Act: -0.0000

Data Index: 256872 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5369. Min Act: -0.0000

Data Index: 927599 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5703. Min Act: -0.0000

Data Index: 287498 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5294. Min Act: -0.0001

Data Index: 738158 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5276. Min Act: -0.0000

Data Index: 420959 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4954. Min Act: -0.0000

Data Index: 264977 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5363. Min Act: -0.0001

Data Index: 364227 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5760. Min Act: -0.0001

Data Index: 39910 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5306. Min Act: -0.0001

Data Index: 976570 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5470. Min Act: -0.0000

Data Index: 807203 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1061774 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5231. Min Act: -0.0000

Data Index: 900855 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5194. Min Act: -0.0001

Data Index: 221211 (C4 (Web Text))

Max Activating Token Index: 472