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

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

Neuron 4480 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.5832. Min Act: -0.0000

Data Index: 140255 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.5101. Min Act: -0.0000

Data Index: 331434 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1204168 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1150012 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4398. Min Act: 0.0000

Data Index: 659050 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4454. Min Act: -0.0000

Data Index: 437736 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4594. Min Act: 0.0000

Data Index: 1197155 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4286. Min Act: 0.0000

Data Index: 902974 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4320. Min Act: -0.0000

Data Index: 291691 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4149. Min Act: -0.0000

Data Index: 605733 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4163. Min Act: 0.0000

Data Index: 1005444 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1207591 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1132021 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4025. Min Act: -0.0000

Data Index: 60559 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3748. Min Act: -0.0000

Data Index: 257323 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1067861 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3926. Min Act: -0.0000

Data Index: 148654 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3854. Min Act: -0.0000

Data Index: 524263 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3969. Min Act: 0.0000

Data Index: 1153226 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3541. Min Act: -0.0000

Data Index: 809573 (C4 (Web Text))

Max Activating Token Index: 368