Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5390 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1913. Min Range: -5.1913
Max Act: 5.1913. Min Act: -0.1700
Data Index: 6166048 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1913. Min Range: -5.1913
Max Act: 5.1288. Min Act: -0.1700
Data Index: 5052614 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1913. Min Range: -5.1913
Max Act: 5.1600. Min Act: -0.1700
Data Index: 2740943 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1913. Min Range: -5.1913
Max Act: 5.0975. Min Act: -0.1700
Data Index: 645629 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1913. Min Range: -5.1913
Max Act: 5.0975. Min Act: -0.1700
Data Index: 2560813 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1913. Min Range: -5.1913
Max Act: 5.0350. Min Act: -0.1700
Data Index: 1406367 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1913. Min Range: -5.1913
Max Act: 5.0350. Min Act: -0.1700
Data Index: 4497603 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.9725. Min Act: -0.1700
Data Index: 8832539 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1913. Min Range: -5.1913
Max Act: 5.0038. Min Act: -0.1700
Data Index: 4931068 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1913. Min Range: -5.1913
Max Act: 5.0038. Min Act: -0.1700
Data Index: 5028679 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.9725. Min Act: -0.1700
Data Index: 1694724 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.9413. Min Act: -0.1700
Data Index: 6824524 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.9100. Min Act: -0.1700
Data Index: 7816726 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.9100. Min Act: -0.1700
Data Index: 8372648 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.9413. Min Act: -0.1700
Data Index: 4422806 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.9100. Min Act: -0.1700
Data Index: 1712174 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.8788. Min Act: -0.1700
Data Index: 4608136 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.8788. Min Act: -0.1700
Data Index: 5433604 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.8788. Min Act: -0.1700
Data Index: 1408606 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1913. Min Range: -5.1913
Max Act: 4.8475. Min Act: -0.1700
Data Index: 2908269 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19