Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.7006. Min Act: -0.1700
Data Index: 3723905 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.3256. Min Act: -0.1700
Data Index: 7388696 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.2006. Min Act: -0.1700
Data Index: 2028827 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.2006. Min Act: -0.1700
Data Index: 8484379 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.2006. Min Act: -0.1700
Data Index: 5419912 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.2006. Min Act: -0.1700
Data Index: 968808 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.2006. Min Act: -0.1700
Data Index: 8507300 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.0756. Min Act: -0.1700
Data Index: 7926094 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.0756. Min Act: -0.1700
Data Index: 7677291 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.0756. Min Act: -0.1700
Data Index: 4033659 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.0756. Min Act: -0.1700
Data Index: 8172719 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7006. Min Range: -8.7006
Max Act: 8.0131. Min Act: -0.1700
Data Index: 5419911 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7006. Min Range: -8.7006
Max Act: 7.9506. Min Act: -0.1700
Data Index: 527919 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7006. Min Range: -8.7006
Max Act: 7.9506. Min Act: -0.1700
Data Index: 4855422 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7006. Min Range: -8.7006
Max Act: 7.8881. Min Act: -0.1700
Data Index: 534042 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7006. Min Range: -8.7006
Max Act: 7.8881. Min Act: -0.1700
Data Index: 4775948 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7006. Min Range: -8.7006
Max Act: 7.8881. Min Act: -0.1700
Data Index: 5530479 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7006. Min Range: -8.7006
Max Act: 7.8881. Min Act: -0.1700
Data Index: 759748 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7006. Min Range: -8.7006
Max Act: 7.8881. Min Act: -0.1700
Data Index: 4027130 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7006. Min Range: -8.7006
Max Act: 7.9506. Min Act: -0.1700
Data Index: 7449692 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19