Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1861 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.9652. Min Act: -0.1700
Data Index: 4793364 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.6838. Min Act: -0.1700
Data Index: 1730769 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.6994. Min Act: -0.1700
Data Index: 7738566 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.6681. Min Act: -0.1700
Data Index: 7537843 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.6681. Min Act: -0.1700
Data Index: 1999235 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.6212. Min Act: -0.1700
Data Index: 5996580 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.6212. Min Act: -0.1700
Data Index: 3462715 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5899. Min Act: -0.1700
Data Index: 2250686 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5899. Min Act: -0.1700
Data Index: 1123554 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.6055. Min Act: -0.1700
Data Index: 7856620 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5742. Min Act: -0.1700
Data Index: 436780 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5586. Min Act: -0.1700
Data Index: 5198193 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5586. Min Act: -0.1700
Data Index: 7164960 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5586. Min Act: -0.1700
Data Index: 1260630 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5429. Min Act: -0.1700
Data Index: 2666375 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5429. Min Act: -0.1700
Data Index: 2420568 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5586. Min Act: -0.1700
Data Index: 8713177 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5742. Min Act: -0.1700
Data Index: 7630700 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5586. Min Act: -0.1700
Data Index: 7557107 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9652. Min Range: -3.9652
Max Act: 3.5116. Min Act: -0.1700
Data Index: 7137099 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19