Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.5904. Min Range: -13.5904
Max Act: 13.5904. Min Act: -0.1700
Data Index: 4102802 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.5904. Min Range: -13.5904
Max Act: 13.2154. Min Act: -0.1700
Data Index: 3865321 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.5904. Min Range: -13.5904
Max Act: 13.1529. Min Act: -0.1700
Data Index: 7968831 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.5904. Min Range: -13.5904
Max Act: 13.2154. Min Act: -0.1700
Data Index: 72006 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.5904. Min Range: -13.5904
Max Act: 13.1529. Min Act: -0.1700
Data Index: 5011644 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.5904. Min Range: -13.5904
Max Act: 13.1529. Min Act: -0.1700
Data Index: 3430193 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.5904. Min Range: -13.5904
Max Act: 13.1529. Min Act: -0.1700
Data Index: 6883864 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.5904. Min Range: -13.5904
Max Act: 13.0904. Min Act: -0.1700
Data Index: 7899465 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.5904. Min Range: -13.5904
Max Act: 13.0904. Min Act: -0.1699
Data Index: 4952519 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.5904. Min Range: -13.5904
Max Act: 13.0279. Min Act: -0.1700
Data Index: 8471183 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.5904. Min Range: -13.5904
Max Act: 12.9654. Min Act: -0.1700
Data Index: 1310877 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.5904. Min Range: -13.5904
Max Act: 12.9654. Min Act: -0.1700
Data Index: 3547741 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.5904. Min Range: -13.5904
Max Act: 12.9654. Min Act: -0.1700
Data Index: 930095 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.5904. Min Range: -13.5904
Max Act: 12.9029. Min Act: -0.1700
Data Index: 5701843 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.5904. Min Range: -13.5904
Max Act: 12.8404. Min Act: -0.1700
Data Index: 2194854 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.5904. Min Range: -13.5904
Max Act: 12.8404. Min Act: -0.1700
Data Index: 2153210 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.5904. Min Range: -13.5904
Max Act: 12.7154. Min Act: -0.1700
Data Index: 3449924 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.5904. Min Range: -13.5904
Max Act: 12.7779. Min Act: -0.1700
Data Index: 4964946 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.5904. Min Range: -13.5904
Max Act: 12.7779. Min Act: -0.1700
Data Index: 79863 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.5904. Min Range: -13.5904
Max Act: 12.7779. Min Act: -0.1700
Data Index: 1101673 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19