Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6057 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.5007. Min Act: -0.1700
Data Index: 5680139 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.4382. Min Act: -0.1700
Data Index: 6084313 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.4382. Min Act: -0.1700
Data Index: 5525930 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.4382. Min Act: -0.1700
Data Index: 6542862 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.4382. Min Act: -0.1700
Data Index: 1610232 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.3757. Min Act: -0.1700
Data Index: 6961867 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.3757. Min Act: -0.1700
Data Index: 8584670 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.4382. Min Act: -0.1700
Data Index: 5445503 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.3132. Min Act: -0.1700
Data Index: 304000 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.3132. Min Act: -0.1700
Data Index: 6542865 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.1882. Min Act: -0.1700
Data Index: 7201286 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.2507. Min Act: -0.1700
Data Index: 3453811 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.1882. Min Act: -0.1700
Data Index: 2707479 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.1882. Min Act: -0.1700
Data Index: 3965405 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.1257. Min Act: -0.1700
Data Index: 1370599 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.1257. Min Act: -0.1700
Data Index: 4781621 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.1257. Min Act: -0.1700
Data Index: 4526822 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.1257. Min Act: -0.1700
Data Index: 502257 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.0632. Min Act: -0.1700
Data Index: 4706619 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5007. Min Range: -8.5007
Max Act: 8.0632. Min Act: -0.1700
Data Index: 475884 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19