Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5492 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1404. Min Range: -5.1404
Max Act: 5.1404. Min Act: -0.1700
Data Index: 1132597 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1404. Min Range: -5.1404
Max Act: 5.0154. Min Act: -0.1700
Data Index: 6621739 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.8279. Min Act: -0.1700
Data Index: 602279 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.6717. Min Act: -0.1700
Data Index: 8357255 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.6717. Min Act: -0.1700
Data Index: 2269658 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.6717. Min Act: -0.1700
Data Index: 6252694 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.6404. Min Act: -0.1700
Data Index: 6273692 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5779. Min Act: -0.1700
Data Index: 693993 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.6092. Min Act: -0.1700
Data Index: 8609499 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5779. Min Act: -0.1700
Data Index: 883931 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5779. Min Act: -0.1700
Data Index: 6418757 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5467. Min Act: -0.1700
Data Index: 6995639 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5779. Min Act: -0.1700
Data Index: 3881922 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5154. Min Act: -0.1700
Data Index: 5215795 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5154. Min Act: -0.1700
Data Index: 5164874 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5154. Min Act: -0.1700
Data Index: 7771603 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5154. Min Act: -0.1700
Data Index: 6892098 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5154. Min Act: -0.1700
Data Index: 3307848 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.5154. Min Act: -0.1700
Data Index: 3182931 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1404. Min Range: -5.1404
Max Act: 4.4842. Min Act: -0.1700
Data Index: 1158386 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19