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

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

Neuron 1374 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.8770. Min Act: -0.0001

Data Index: 1016312 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.8234. Min Act: -0.0001

Data Index: 543896 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7039. Min Act: -0.0001

Data Index: 1347428 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5968. Min Act: -0.0001

Data Index: 203616 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5891. Min Act: -0.0001

Data Index: 886115 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5818. Min Act: -0.0001

Data Index: 460976 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.6161. Min Act: -0.0001

Data Index: 581587 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5960. Min Act: -0.0001

Data Index: 182847 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5843. Min Act: -0.0001

Data Index: 255696 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5849. Min Act: -0.0001

Data Index: 1209190 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5782. Min Act: -0.0001

Data Index: 384795 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5593. Min Act: -0.0001

Data Index: 711241 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5192. Min Act: -0.0001

Data Index: 47968 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5697. Min Act: -0.0001

Data Index: 638715 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5621. Min Act: -0.0001

Data Index: 43442 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.6016. Min Act: -0.0001

Data Index: 1016769 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5454. Min Act: -0.0001

Data Index: 76231 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5431. Min Act: -0.0001

Data Index: 1226410 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5411. Min Act: -0.0001

Data Index: 85802 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5666. Min Act: -0.0001

Data Index: 1245355 (C4 (Web Text))

Max Activating Token Index: 758