Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.8025. Min Act: -0.1700
Data Index: 2934951 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.7400. Min Act: -0.1700
Data Index: 775300 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.7400. Min Act: -0.1700
Data Index: 7891103 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.7087. Min Act: -0.1700
Data Index: 1364816 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.6775. Min Act: -0.1700
Data Index: 2284634 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.6462. Min Act: -0.1700
Data Index: 7954979 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.6462. Min Act: -0.1700
Data Index: 6713355 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.6150. Min Act: -0.1700
Data Index: 8242268 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5837. Min Act: -0.1700
Data Index: 2901351 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5837. Min Act: -0.1700
Data Index: 1512658 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5837. Min Act: -0.1700
Data Index: 8219908 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5525. Min Act: -0.1700
Data Index: 2108722 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5525. Min Act: -0.1700
Data Index: 5997886 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5525. Min Act: -0.1700
Data Index: 3238622 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5525. Min Act: -0.1700
Data Index: 4201215 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5525. Min Act: -0.1700
Data Index: 1161351 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5212. Min Act: -0.1700
Data Index: 4082688 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5525. Min Act: -0.1700
Data Index: 6841688 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5212. Min Act: -0.1700
Data Index: 350906 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8025. Min Range: -5.8025
Max Act: 5.5212. Min Act: -0.1700
Data Index: 2739439 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19