Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2986 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.4261. Min Act: -0.0003
Data Index: 769592 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.5388. Min Act: -0.0003
Data Index: 13911 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2827. Min Act: -0.0003
Data Index: 830445 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.3019. Min Act: -0.0003
Data Index: 1868416 (The Pile)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.1492. Min Act: -0.0003
Data Index: 1156238 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2450. Min Act: -0.0003
Data Index: 1518460 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2044. Min Act: -0.0003
Data Index: 1073186 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2326. Min Act: -0.0003
Data Index: 254400 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2333. Min Act: -0.0003
Data Index: 446607 (The Pile)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2695. Min Act: -0.0003
Data Index: 1175786 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.1807. Min Act: -0.0003
Data Index: 1618325 (The Pile)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2473. Min Act: -0.0003
Data Index: 730225 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2171. Min Act: -0.0003
Data Index: 1219381 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2837. Min Act: -0.0003
Data Index: 787610 (The Pile)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.1778. Min Act: -0.0003
Data Index: 1941122 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2018. Min Act: -0.0003
Data Index: 942472 (The Pile)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2018. Min Act: -0.0003
Data Index: 1354008 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.1979. Min Act: -0.0003
Data Index: 206075 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.2042. Min Act: -0.0003
Data Index: 795869 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5388. Min Range: -1.5388
Max Act: 1.1635. Min Act: -0.0003
Data Index: 145828 (The Pile)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19