Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3746 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2768. Min Range: -7.2768
Max Act: 7.2768. Min Act: -0.1700
Data Index: 4891315 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.8706. Min Act: -0.1700
Data Index: 413069 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.8706. Min Act: -0.1700
Data Index: 8516955 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.7768. Min Act: -0.1700
Data Index: 7929384 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.7768. Min Act: -0.1700
Data Index: 4211714 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.7456. Min Act: -0.1700
Data Index: 1010695 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.7768. Min Act: -0.1700
Data Index: 1891180 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.7143. Min Act: -0.1700
Data Index: 1214698 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.6831. Min Act: -0.1700
Data Index: 8818627 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.6518. Min Act: -0.1700
Data Index: 4338631 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.6518. Min Act: -0.1700
Data Index: 4849334 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.6518. Min Act: -0.1700
Data Index: 3372144 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.5581. Min Act: -0.1700
Data Index: 3420132 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.5581. Min Act: -0.1700
Data Index: 6215740 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.5581. Min Act: -0.1700
Data Index: 7976092 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.4956. Min Act: -0.1700
Data Index: 3420129 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.4956. Min Act: -0.1700
Data Index: 5943237 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.4956. Min Act: -0.1700
Data Index: 7049395 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.4643. Min Act: -0.1700
Data Index: 1801007 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2768. Min Range: -7.2768
Max Act: 6.4331. Min Act: -0.1700
Data Index: 7218681 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19