Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.4903. Min Act: -0.1700
Data Index: 1024179 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.4903. Min Act: -0.1700
Data Index: 1123049 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.2403. Min Act: -0.1700
Data Index: 4988632 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.2403. Min Act: -0.1700
Data Index: 849437 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.2403. Min Act: -0.1700
Data Index: 7125456 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.1778. Min Act: -0.1700
Data Index: 8038909 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.1778. Min Act: -0.1700
Data Index: 557677 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.1778. Min Act: -0.1700
Data Index: 1343577 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.1778. Min Act: -0.1700
Data Index: 5556779 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.1153. Min Act: -0.1700
Data Index: 6079830 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.0528. Min Act: -0.1700
Data Index: 909625 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4903. Min Range: -8.4903
Max Act: 8.0528. Min Act: -0.1700
Data Index: 2213657 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4903. Min Range: -8.4903
Max Act: 7.9903. Min Act: -0.1700
Data Index: 968660 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4903. Min Range: -8.4903
Max Act: 7.9278. Min Act: -0.1700
Data Index: 1023309 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4903. Min Range: -8.4903
Max Act: 7.9278. Min Act: -0.1700
Data Index: 2858033 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4903. Min Range: -8.4903
Max Act: 7.9278. Min Act: -0.1700
Data Index: 4441074 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4903. Min Range: -8.4903
Max Act: 7.8653. Min Act: -0.1700
Data Index: 1696131 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4903. Min Range: -8.4903
Max Act: 7.8653. Min Act: -0.1700
Data Index: 712760 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4903. Min Range: -8.4903
Max Act: 7.8653. Min Act: -0.1700
Data Index: 2471852 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4903. Min Range: -8.4903
Max Act: 7.8653. Min Act: -0.1700
Data Index: 1513031 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19