Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2969 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0723. Min Range: -6.0723
Max Act: 6.0723. Min Act: -0.1700
Data Index: 7491740 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.9161. Min Act: -0.1700
Data Index: 4304563 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.9161. Min Act: -0.1700
Data Index: 2641166 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.9161. Min Act: -0.1700
Data Index: 785885 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8848. Min Act: -0.1700
Data Index: 804650 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8848. Min Act: -0.1700
Data Index: 5391373 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8848. Min Act: -0.1700
Data Index: 6868083 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8536. Min Act: -0.1699
Data Index: 5578067 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8536. Min Act: -0.1700
Data Index: 4545667 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8848. Min Act: -0.1700
Data Index: 4395896 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8223. Min Act: -0.1700
Data Index: 5391377 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8536. Min Act: -0.1700
Data Index: 642490 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8536. Min Act: -0.1699
Data Index: 752737 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8223. Min Act: -0.1700
Data Index: 7437577 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8223. Min Act: -0.1700
Data Index: 6673932 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8223. Min Act: -0.1700
Data Index: 825114 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8223. Min Act: -0.1699
Data Index: 2565512 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.7911. Min Act: -0.1700
Data Index: 6122387 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8223. Min Act: -0.1700
Data Index: 5735718 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0723. Min Range: -6.0723
Max Act: 5.8223. Min Act: -0.1700
Data Index: 2815646 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19