Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3340 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.7917. Min Act: -0.0001
Data Index: 1807602 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.7222. Min Act: -0.0001
Data Index: 1241180 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.6155. Min Act: -0.0001
Data Index: 562622 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5975. Min Act: -0.0001
Data Index: 1284589 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.6487. Min Act: -0.0001
Data Index: 1913635 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5894. Min Act: -0.0001
Data Index: 320106 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.6233. Min Act: -0.0001
Data Index: 543682 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5619. Min Act: -0.0001
Data Index: 653457 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5823. Min Act: -0.0001
Data Index: 238479 (The Pile)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5766. Min Act: -0.0001
Data Index: 456966 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5611. Min Act: -0.0001
Data Index: 1354489 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5630. Min Act: -0.0001
Data Index: 588788 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.6104. Min Act: -0.0001
Data Index: 1743493 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5921. Min Act: -0.0001
Data Index: 1638448 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5668. Min Act: -0.0001
Data Index: 621006 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5485. Min Act: -0.0001
Data Index: 606539 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5455. Min Act: -0.0001
Data Index: 1462413 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5114. Min Act: -0.0001
Data Index: 1166580 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5540. Min Act: -0.0001
Data Index: 964599 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7917. Min Range: -0.7917
Max Act: 0.5397. Min Act: -0.0001
Data Index: 1266154 (The Pile)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19