Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4315 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2998. Min Range: -8.2998
Max Act: 8.2998. Min Act: -0.1700
Data Index: 8181934 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2998. Min Range: -8.2998
Max Act: 8.2373. Min Act: -0.1700
Data Index: 7674749 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2998. Min Range: -8.2998
Max Act: 8.1123. Min Act: -0.1700
Data Index: 2896605 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2998. Min Range: -8.2998
Max Act: 8.1123. Min Act: -0.1700
Data Index: 5255957 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.8623. Min Act: -0.1700
Data Index: 205593 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.7061. Min Act: -0.1700
Data Index: 1342509 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.7061. Min Act: -0.1700
Data Index: 7427617 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.6748. Min Act: -0.1700
Data Index: 3547286 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.7061. Min Act: -0.1700
Data Index: 2069860 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.7061. Min Act: -0.1700
Data Index: 8696229 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.6748. Min Act: -0.1700
Data Index: 8652854 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.6123. Min Act: -0.1700
Data Index: 7699388 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.6123. Min Act: -0.1700
Data Index: 936844 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.5811. Min Act: -0.1700
Data Index: 1650011 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.5811. Min Act: -0.1700
Data Index: 8059487 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.4873. Min Act: -0.1700
Data Index: 7707461 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.4873. Min Act: -0.1700
Data Index: 1566140 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.4561. Min Act: -0.1700
Data Index: 7653010 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.4248. Min Act: -0.1700
Data Index: 8537130 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2998. Min Range: -8.2998
Max Act: 7.4248. Min Act: -0.1700
Data Index: 4688770 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19