Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5056 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.8004. Min Act: -0.0000

Data Index: 718934 (The Pile)

Max Activating Token Index: 379

Text #1

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.4805. Min Act: -0.0000

Data Index: 1291179 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.4101. Min Act: -0.0000

Data Index: 1559080 (The Pile)

Max Activating Token Index: 212

Text #3

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1588092 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.3065. Min Act: -0.0000

Data Index: 530740 (The Pile)

Max Activating Token Index: 843

Text #5

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.5499. Min Act: -0.0000

Data Index: 159514 (The Pile)

Max Activating Token Index: 687

Text #6

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.3929. Min Act: -0.0000

Data Index: 1145046 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.3100. Min Act: -0.0000

Data Index: 701770 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.1336. Min Act: -0.0000

Data Index: 1473653 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.2503. Min Act: -0.0000

Data Index: 1796464 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1088241 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 1.8004. Min Range: -1.8004

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1951204 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.0849. Min Act: -0.0000

Data Index: 274088 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 1.8004. Min Range: -1.8004

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1052231 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.1274. Min Act: -0.0000

Data Index: 1606354 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 1.8004. Min Range: -1.8004

Max Act: 0.9763. Min Act: -0.0000

Data Index: 420048 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1538929 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 1.8004. Min Range: -1.8004

Max Act: 1.0360. Min Act: -0.0000

Data Index: 564587 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 1.8004. Min Range: -1.8004

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1562280 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 1.8004. Min Range: -1.8004

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1433457 (The Pile)

Max Activating Token Index: 660