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

Dataset: The Pile

Neuron 2756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1917032 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3372. Min Act: -0.0000

Data Index: 694854 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1029690 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3722. Min Act: -0.0000

Data Index: 998096 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3252. Min Act: 0.0000

Data Index: 1141981 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1761312 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3109. Min Act: 0.0000

Data Index: 363650 (The Pile)

Max Activating Token Index: 127

Text #7

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1289730 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3101. Min Act: -0.0000

Data Index: 307459 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1944160 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1764523 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1390555 (The Pile)

Max Activating Token Index: 627

Text #12

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2967. Min Act: 0.0000

Data Index: 1622004 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2938. Min Act: -0.0000

Data Index: 106598 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2868. Min Act: -0.0000

Data Index: 158933 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1822428 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2800. Min Act: -0.0000

Data Index: 337147 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2361. Min Act: -0.0000

Data Index: 359203 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2587. Min Act: -0.0000

Data Index: 533436 (The Pile)

Max Activating Token Index: 882

Text #19

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2720. Min Act: -0.0000

Data Index: 624522 (The Pile)

Max Activating Token Index: 68