Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1060 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4934. Min Range: -8.4934
Max Act: 8.4934. Min Act: -0.1700
Data Index: 5406063 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4934. Min Range: -8.4934
Max Act: 8.0559. Min Act: -0.1700
Data Index: 5007161 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.9309. Min Act: -0.1700
Data Index: 2448818 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.8684. Min Act: -0.1700
Data Index: 2654890 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.5871. Min Act: -0.1700
Data Index: 2489442 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.5871. Min Act: -0.1700
Data Index: 6509150 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.5871. Min Act: -0.1700
Data Index: 3687173 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.5559. Min Act: -0.1700
Data Index: 150290 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.5559. Min Act: -0.1700
Data Index: 7203066 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.4309. Min Act: -0.1700
Data Index: 3365141 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.4621. Min Act: -0.1700
Data Index: 8758326 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.3371. Min Act: -0.1700
Data Index: 833255 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.2434. Min Act: -0.1700
Data Index: 4027368 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.2434. Min Act: -0.1700
Data Index: 2106563 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.2121. Min Act: -0.1700
Data Index: 6708377 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.2121. Min Act: -0.1700
Data Index: 3383603 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.2121. Min Act: -0.1700
Data Index: 8468439 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.1809. Min Act: -0.1700
Data Index: 240311 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.1809. Min Act: -0.1700
Data Index: 8027118 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4934. Min Range: -8.4934
Max Act: 7.1809. Min Act: -0.1700
Data Index: 5190885 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19