Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5200 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.3139. Min Act: -0.1700
Data Index: 3559009 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.1576. Min Act: -0.1700
Data Index: 4858406 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.1264. Min Act: -0.1700
Data Index: 453483 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.0639. Min Act: -0.1700
Data Index: 2500981 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.8139. Min Act: -0.1700
Data Index: 6823627 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.7201. Min Act: -0.1699
Data Index: 8471542 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.7201. Min Act: -0.1700
Data Index: 7528632 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.6889. Min Act: -0.1700
Data Index: 2500979 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.6576. Min Act: -0.1700
Data Index: 6308043 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.6576. Min Act: -0.1700
Data Index: 6576946 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.6264. Min Act: -0.1700
Data Index: 179781 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.6264. Min Act: -0.1700
Data Index: 6228133 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.6264. Min Act: -0.1700
Data Index: 6428914 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.6264. Min Act: -0.1700
Data Index: 8001086 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.5951. Min Act: -0.1700
Data Index: 894948 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.6264. Min Act: -0.1700
Data Index: 3485373 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.5951. Min Act: -0.1700
Data Index: 814920 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.5639. Min Act: -0.1700
Data Index: 203544 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.5639. Min Act: -0.1700
Data Index: 127085 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.5326. Min Act: -0.1700
Data Index: 272438 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19