Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3231 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 6.5904. Min Range: -6.5904
Max Act: 6.5904. Min Act: -0.0000
Data Index: 1197222 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5904. Min Range: -6.5904
Max Act: 5.8327. Min Act: -0.0000
Data Index: 1578917 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5904. Min Range: -6.5904
Max Act: 5.5570. Min Act: -0.0000
Data Index: 153029 (The Pile)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5904. Min Range: -6.5904
Max Act: 5.2320. Min Act: -0.0000
Data Index: 1077803 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5904. Min Range: -6.5904
Max Act: 4.7315. Min Act: -0.0000
Data Index: 1569889 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5904. Min Range: -6.5904
Max Act: 4.5292. Min Act: -0.0000
Data Index: 1780057 (The Pile)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5904. Min Range: -6.5904
Max Act: 4.4624. Min Act: -0.0000
Data Index: 1414517 (The Pile)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5904. Min Range: -6.5904
Max Act: 4.0019. Min Act: -0.0000
Data Index: 1167430 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5904. Min Range: -6.5904
Max Act: 4.3812. Min Act: -0.0000
Data Index: 355069 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5904. Min Range: -6.5904
Max Act: 4.0563. Min Act: -0.0000
Data Index: 144826 (The Pile)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5904. Min Range: -6.5904
Max Act: 3.5376. Min Act: -0.0000
Data Index: 723914 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5904. Min Range: -6.5904
Max Act: 3.8053. Min Act: -0.0000
Data Index: 244008 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5904. Min Range: -6.5904
Max Act: 3.1907. Min Act: -0.0000
Data Index: 165263 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5904. Min Range: -6.5904
Max Act: 3.5938. Min Act: -0.0000
Data Index: 1608725 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5904. Min Range: -6.5904
Max Act: 3.5787. Min Act: -0.0000
Data Index: 222723 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5904. Min Range: -6.5904
Max Act: 3.3377. Min Act: -0.0000
Data Index: 1915900 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5904. Min Range: -6.5904
Max Act: 3.5175. Min Act: -0.0000
Data Index: 554337 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5904. Min Range: -6.5904
Max Act: 3.1281. Min Act: -0.0000
Data Index: 1941699 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5904. Min Range: -6.5904
Max Act: 2.9542. Min Act: -0.0000
Data Index: 483261 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5904. Min Range: -6.5904
Max Act: 3.6656. Min Act: -0.0000
Data Index: 14773 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19