Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3451 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0810. Min Act: -0.0001
Data Index: 876239 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0733. Min Act: -0.0001
Data Index: 147919 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0794. Min Act: -0.0001
Data Index: 824816 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0760. Min Act: -0.0001
Data Index: 880483 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0689. Min Act: -0.0001
Data Index: 844186 (The Pile)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0695. Min Act: -0.0001
Data Index: 1323667 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0695. Min Act: -0.0001
Data Index: 1690456 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0695. Min Act: -0.0001
Data Index: 1034915 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0656. Min Act: -0.0001
Data Index: 1679477 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0714. Min Act: -0.0001
Data Index: 343767 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0702. Min Act: -0.0001
Data Index: 1954561 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0656. Min Act: -0.0001
Data Index: 1992272 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0609. Min Act: -0.0001
Data Index: 414497 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0630. Min Act: -0.0001
Data Index: 1855228 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0646. Min Act: -0.0001
Data Index: 1136409 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0645. Min Act: -0.0001
Data Index: 474443 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0619. Min Act: -0.0001
Data Index: 844061 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0719. Min Act: -0.0001
Data Index: 1544388 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0663. Min Act: -0.0001
Data Index: 966738 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0810. Min Range: -0.0810
Max Act: 0.0585. Min Act: -0.0001
Data Index: 824045 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19