Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1265 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.5527. Min Act: -0.0002
Data Index: 1497255 (The Pile)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.5682. Min Act: -0.0002
Data Index: 474317 (The Pile)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.4344. Min Act: -0.0002
Data Index: 1571041 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3913. Min Act: -0.0002
Data Index: 1963238 (The Pile)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3432. Min Act: -0.0002
Data Index: 55252 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3541. Min Act: -0.0002
Data Index: 1399733 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.2896. Min Act: -0.0002
Data Index: 674790 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3618. Min Act: -0.0002
Data Index: 173114 (The Pile)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3231. Min Act: -0.0002
Data Index: 297565 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3612. Min Act: -0.0002
Data Index: 1475683 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3037. Min Act: -0.0002
Data Index: 1375250 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3797. Min Act: -0.0002
Data Index: 391122 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.2988. Min Act: -0.0002
Data Index: 1050680 (The Pile)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3034. Min Act: -0.0002
Data Index: 688632 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3804. Min Act: -0.0002
Data Index: 381682 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3339. Min Act: -0.0002
Data Index: 1622128 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3012. Min Act: -0.0002
Data Index: 1585487 (The Pile)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.2890. Min Act: -0.0002
Data Index: 1944753 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3302. Min Act: -0.0002
Data Index: 165498 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5682. Min Range: -1.5682
Max Act: 1.3128. Min Act: -0.0002
Data Index: 692455 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19