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

Dataset: The Pile

Neuron 3014 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1239551 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.7780. Min Act: -0.0000

Data Index: 939931 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.6384. Min Act: -0.0000

Data Index: 575635 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.5401. Min Act: -0.0000

Data Index: 460470 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.6134. Min Act: -0.0000

Data Index: 93877 (The Pile)

Max Activating Token Index: 770

Text #5

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.6128. Min Act: -0.0000

Data Index: 1610516 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.5617. Min Act: -0.0000

Data Index: 1150421 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.5077. Min Act: -0.0000

Data Index: 940356 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.6014. Min Act: -0.0000

Data Index: 242362 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.4314. Min Act: -0.0000

Data Index: 1325649 (The Pile)

Max Activating Token Index: 955

Text #10

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.4918. Min Act: -0.0000

Data Index: 718650 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.4984. Min Act: -0.0000

Data Index: 1923088 (The Pile)

Max Activating Token Index: 844

Text #12

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.4675. Min Act: -0.0000

Data Index: 1031529 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.3829. Min Act: -0.0000

Data Index: 535678 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.4522. Min Act: -0.0000

Data Index: 759850 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.4500. Min Act: -0.0000

Data Index: 1553749 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.3544. Min Act: -0.0000

Data Index: 266363 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.4500. Min Act: -0.0000

Data Index: 1601729 (The Pile)

Max Activating Token Index: 620

Text #18

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.4330. Min Act: -0.0000

Data Index: 296990 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 1.7780. Min Range: -1.7780

Max Act: 1.3763. Min Act: -0.0000

Data Index: 132601 (The Pile)

Max Activating Token Index: 762