Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.3119. Min Act: -0.1700
Data Index: 4008188 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.2807. Min Act: -0.1700
Data Index: 6077679 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.2182. Min Act: -0.1700
Data Index: 4962499 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.1557. Min Act: -0.1700
Data Index: 5684823 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.1557. Min Act: -0.1700
Data Index: 3510208 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.1244. Min Act: -0.1700
Data Index: 5008785 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0619. Min Act: -0.1700
Data Index: 3147756 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0932. Min Act: -0.1700
Data Index: 6224392 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0932. Min Act: -0.1700
Data Index: 4070983 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0619. Min Act: -0.1700
Data Index: 6948725 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0619. Min Act: -0.1700
Data Index: 2447083 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0619. Min Act: -0.1700
Data Index: 3260421 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0619. Min Act: -0.1700
Data Index: 3553939 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0307. Min Act: -0.1700
Data Index: 3695552 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3119. Min Range: -5.3119
Max Act: 4.9994. Min Act: -0.1700
Data Index: 8337784 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0619. Min Act: -0.1700
Data Index: 5739739 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0307. Min Act: -0.1700
Data Index: 297336 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3119. Min Range: -5.3119
Max Act: 5.0307. Min Act: -0.1700
Data Index: 5286675 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3119. Min Range: -5.3119
Max Act: 4.9682. Min Act: -0.1700
Data Index: 3975086 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3119. Min Range: -5.3119
Max Act: 4.9994. Min Act: -0.1700
Data Index: 1597621 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19