Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4620. Min Range: -8.4620
Max Act: 8.4620. Min Act: -0.1700
Data Index: 8129709 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4620. Min Range: -8.4620
Max Act: 8.1182. Min Act: -0.1700
Data Index: 3825910 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4620. Min Range: -8.4620
Max Act: 8.0557. Min Act: -0.1700
Data Index: 7483133 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4620. Min Range: -8.4620
Max Act: 8.0557. Min Act: -0.1700
Data Index: 6827782 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4620. Min Range: -8.4620
Max Act: 8.0557. Min Act: -0.1700
Data Index: 5029569 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4620. Min Range: -8.4620
Max Act: 8.0245. Min Act: -0.1700
Data Index: 4188379 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4620. Min Range: -8.4620
Max Act: 8.0245. Min Act: -0.1700
Data Index: 670568 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.9620. Min Act: -0.1700
Data Index: 2673606 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.8995. Min Act: -0.1700
Data Index: 1339211 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.8995. Min Act: -0.1700
Data Index: 2882596 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.8682. Min Act: -0.1700
Data Index: 3790259 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.8057. Min Act: -0.1700
Data Index: 2750061 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.7120. Min Act: -0.1700
Data Index: 7932366 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.6807. Min Act: -0.1700
Data Index: 8146061 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.6807. Min Act: -0.1700
Data Index: 3257279 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.7120. Min Act: -0.1700
Data Index: 4394698 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.6807. Min Act: -0.1700
Data Index: 4408372 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.6495. Min Act: -0.1700
Data Index: 1783443 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.6495. Min Act: -0.1700
Data Index: 5244127 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4620. Min Range: -8.4620
Max Act: 7.6495. Min Act: -0.1700
Data Index: 3291143 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19