Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0597. Min Range: -2.0597
Max Act: 2.0597. Min Act: -0.1700
Data Index: 8715853 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.9754. Min Act: -0.1700
Data Index: 2904623 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.9244. Min Act: -0.1700
Data Index: 751697 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.9074. Min Act: -0.1700
Data Index: 5864537 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.9074. Min Act: -0.1700
Data Index: 264581 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.9074. Min Act: -0.1700
Data Index: 7744381 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8904. Min Act: -0.1700
Data Index: 7341058 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8733. Min Act: -0.1700
Data Index: 4684115 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8733. Min Act: -0.1700
Data Index: 834553 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8390. Min Act: -0.1700
Data Index: 7469764 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8562. Min Act: -0.1700
Data Index: 4236544 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8733. Min Act: -0.1700
Data Index: 8420908 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8562. Min Act: -0.1700
Data Index: 5633824 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8562. Min Act: -0.1700
Data Index: 7421992 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8390. Min Act: -0.1700
Data Index: 2753682 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8390. Min Act: -0.1700
Data Index: 6863303 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8219. Min Act: -0.1700
Data Index: 1331829 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8219. Min Act: -0.1700
Data Index: 5726358 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8047. Min Act: -0.1700
Data Index: 3880575 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0597. Min Range: -2.0597
Max Act: 1.8047. Min Act: -0.1700
Data Index: 631742 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19