Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5970 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1774. Min Range: -7.1774
Max Act: 7.1774. Min Act: -0.1700
Data Index: 5008300 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1774. Min Range: -7.1774
Max Act: 7.1462. Min Act: -0.1700
Data Index: 2854365 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.9899. Min Act: -0.1700
Data Index: 3648218 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.9587. Min Act: -0.1700
Data Index: 6471197 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.9587. Min Act: -0.1700
Data Index: 2859125 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.9587. Min Act: -0.1700
Data Index: 6618320 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.8024. Min Act: -0.1700
Data Index: 5349228 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.8024. Min Act: -0.1700
Data Index: 4623012 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7712. Min Act: -0.1700
Data Index: 3151713 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7712. Min Act: -0.1700
Data Index: 5344661 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7399. Min Act: -0.1700
Data Index: 6169153 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7399. Min Act: -0.1700
Data Index: 7287859 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7399. Min Act: -0.1700
Data Index: 6683722 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7712. Min Act: -0.1700
Data Index: 8393315 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7399. Min Act: -0.1700
Data Index: 850585 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7399. Min Act: -0.1700
Data Index: 4643149 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7399. Min Act: -0.1700
Data Index: 7806594 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7087. Min Act: -0.1700
Data Index: 618392 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7087. Min Act: -0.1700
Data Index: 5374296 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1774. Min Range: -7.1774
Max Act: 6.7087. Min Act: -0.1700
Data Index: 8320175 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19