Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6051 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.7026. Min Act: -0.1700
Data Index: 6690704 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.2026. Min Act: -0.1700
Data Index: 5368097 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.2026. Min Act: -0.1700
Data Index: 4585832 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.1401. Min Act: -0.1700
Data Index: 7272900 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.1401. Min Act: -0.1700
Data Index: 8284782 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.0776. Min Act: -0.1700
Data Index: 1351338 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.0776. Min Act: -0.1700
Data Index: 7109834 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.0776. Min Act: -0.1694
Data Index: 2092752 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.0151. Min Act: -0.1700
Data Index: 8744393 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.0151. Min Act: -0.1700
Data Index: 2157 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.0151. Min Act: -0.1700
Data Index: 1402783 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.0151. Min Act: -0.1700
Data Index: 2562849 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7026. Min Range: -10.7026
Max Act: 10.0151. Min Act: -0.1700
Data Index: 5196078 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7026. Min Range: -10.7026
Max Act: 9.8901. Min Act: -0.1700
Data Index: 1472555 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7026. Min Range: -10.7026
Max Act: 9.9526. Min Act: -0.1700
Data Index: 4410973 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7026. Min Range: -10.7026
Max Act: 9.9526. Min Act: -0.1700
Data Index: 4083007 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7026. Min Range: -10.7026
Max Act: 9.8901. Min Act: -0.1700
Data Index: 1398419 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7026. Min Range: -10.7026
Max Act: 9.8901. Min Act: -0.1700
Data Index: 1977913 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7026. Min Range: -10.7026
Max Act: 9.8901. Min Act: -0.1700
Data Index: 7109815 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7026. Min Range: -10.7026
Max Act: 9.8276. Min Act: -0.1700
Data Index: 5012096 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19