Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 946 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3947. Min Range: -7.3947
Max Act: 7.3947. Min Act: -0.1700
Data Index: 5409010 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3947. Min Range: -7.3947
Max Act: 7.2072. Min Act: -0.1700
Data Index: 7508191 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3947. Min Range: -7.3947
Max Act: 7.2072. Min Act: -0.1700
Data Index: 270674 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3947. Min Range: -7.3947
Max Act: 7.1760. Min Act: -0.1700
Data Index: 7442445 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3947. Min Range: -7.3947
Max Act: 7.0510. Min Act: -0.1700
Data Index: 4479857 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3947. Min Range: -7.3947
Max Act: 7.0510. Min Act: -0.1700
Data Index: 7739232 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3947. Min Range: -7.3947
Max Act: 7.0197. Min Act: -0.1700
Data Index: 2017760 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.9885. Min Act: -0.1700
Data Index: 3313442 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.9885. Min Act: -0.1700
Data Index: 8734630 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.9572. Min Act: -0.1700
Data Index: 6989764 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.9260. Min Act: -0.1700
Data Index: 7479040 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.8635. Min Act: -0.1700
Data Index: 2951436 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.8322. Min Act: -0.1700
Data Index: 6312373 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.8322. Min Act: -0.1700
Data Index: 1421826 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.8010. Min Act: -0.1700
Data Index: 1174059 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.8010. Min Act: -0.1700
Data Index: 6568655 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.8010. Min Act: -0.1700
Data Index: 4173759 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.7385. Min Act: -0.1700
Data Index: 6000139 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.7385. Min Act: -0.1700
Data Index: 384275 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3947. Min Range: -7.3947
Max Act: 6.7385. Min Act: -0.1700
Data Index: 1160359 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19