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

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

Neuron 3004 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8739. Min Act: -0.0001

Data Index: 521404 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7990. Min Act: -0.0001

Data Index: 247232 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7812. Min Act: -0.0001

Data Index: 1009175 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7964. Min Act: -0.0001

Data Index: 1156597 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8604. Min Act: -0.0001

Data Index: 93344 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8117. Min Act: -0.0001

Data Index: 991103 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8732. Min Act: -0.0001

Data Index: 337896 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6494. Min Act: -0.0001

Data Index: 963569 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7387. Min Act: -0.0001

Data Index: 814205 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7641. Min Act: -0.0001

Data Index: 752078 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7350. Min Act: -0.0001

Data Index: 507908 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7581. Min Act: -0.0001

Data Index: 570782 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8018. Min Act: -0.0001

Data Index: 598144 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7460. Min Act: -0.0001

Data Index: 140646 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7415. Min Act: -0.0001

Data Index: 1267758 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7409. Min Act: -0.0001

Data Index: 512889 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7067. Min Act: -0.0001

Data Index: 983194 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6227. Min Act: -0.0001

Data Index: 859012 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7219. Min Act: -0.0001

Data Index: 541464 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6708. Min Act: -0.0001

Data Index: 489192 (C4 (Web Text))

Max Activating Token Index: 1005