Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.3100. Min Act: -0.1700
Data Index: 803446 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.1225. Min Act: -0.1700
Data Index: 5481750 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.0913. Min Act: -0.1700
Data Index: 6710051 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.0913. Min Act: -0.1700
Data Index: 279509 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3100. Min Range: -6.3100
Max Act: 6.0600. Min Act: -0.1700
Data Index: 8396247 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8725. Min Act: -0.1700
Data Index: 171566 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8725. Min Act: -0.1700
Data Index: 7999050 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8413. Min Act: -0.1700
Data Index: 7107203 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8413. Min Act: -0.1700
Data Index: 6087531 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8413. Min Act: -0.1700
Data Index: 3073493 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8100. Min Act: -0.1700
Data Index: 4064614 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8100. Min Act: -0.1700
Data Index: 5133244 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.8100. Min Act: -0.1700
Data Index: 3993733 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.7788. Min Act: -0.1700
Data Index: 3877169 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.7788. Min Act: -0.1700
Data Index: 2349289 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.7475. Min Act: -0.1700
Data Index: 7848824 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.7163. Min Act: -0.1700
Data Index: 5556657 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.7163. Min Act: -0.1700
Data Index: 6592676 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.7163. Min Act: -0.1700
Data Index: 7168044 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3100. Min Range: -6.3100
Max Act: 5.7163. Min Act: -0.1700
Data Index: 6701903 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19