Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 636 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.8083. Min Act: -0.0000
Data Index: 1624841 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.9936. Min Act: -0.0000
Data Index: 463780 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.9936. Min Act: -0.0000
Data Index: 231330 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.9370. Min Act: -0.0000
Data Index: 1326483 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.7984. Min Act: -0.0000
Data Index: 1453097 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.8004. Min Act: -0.0000
Data Index: 1148952 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.8952. Min Act: -0.0000
Data Index: 1626054 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.6014. Min Act: -0.0000
Data Index: 1827492 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.5095. Min Act: -0.0000
Data Index: 1844017 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.8809. Min Act: -0.0000
Data Index: 1366521 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.7752. Min Act: -0.0000
Data Index: 26391 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.7752. Min Act: -0.0000
Data Index: 151544 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.7752. Min Act: -0.0000
Data Index: 335698 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.5926. Min Act: -0.0000
Data Index: 1585758 (The Pile)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.5722. Min Act: -0.0000
Data Index: 169337 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.5778. Min Act: -0.0000
Data Index: 75370 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.5570. Min Act: -0.0000
Data Index: 464904 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.5492. Min Act: -0.0000
Data Index: 1503230 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.5492. Min Act: -0.0000
Data Index: 1579612 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9936. Min Range: -2.9936
Max Act: 2.5492. Min Act: -0.0000
Data Index: 1358271 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19