Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1933 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.3733. Min Act: -0.0000
Data Index: 592459 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.3789. Min Act: -0.0000
Data Index: 368074 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.3139. Min Act: -0.0000
Data Index: 1231501 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.3789. Min Act: -0.0001
Data Index: 1745981 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.3605. Min Act: -0.0000
Data Index: 792013 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.3035. Min Act: -0.0000
Data Index: 240575 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.3126. Min Act: -0.0000
Data Index: 1989828 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2870. Min Act: -0.0000
Data Index: 1443634 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2962. Min Act: -0.0000
Data Index: 309009 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2622. Min Act: -0.0001
Data Index: 31026 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.3108. Min Act: -0.0000
Data Index: 436234 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2866. Min Act: -0.0001
Data Index: 1997809 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2736. Min Act: -0.0000
Data Index: 351729 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2799. Min Act: -0.0000
Data Index: 1719996 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2931. Min Act: -0.0000
Data Index: 1865998 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2882. Min Act: -0.0000
Data Index: 736998 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2605. Min Act: -0.0000
Data Index: 1901488 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2784. Min Act: -0.0001
Data Index: 903365 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2560. Min Act: -0.0001
Data Index: 372035 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3789. Min Range: -0.3789
Max Act: 0.2447. Min Act: -0.0000
Data Index: 225528 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19