Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3748 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1037. Min Range: -5.1037
Max Act: 5.1037. Min Act: -0.1700
Data Index: 3527808 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1037. Min Range: -5.1037
Max Act: 5.0724. Min Act: -0.1700
Data Index: 5066093 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1037. Min Range: -5.1037
Max Act: 5.0099. Min Act: -0.1700
Data Index: 6290858 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1037. Min Range: -5.1037
Max Act: 5.0412. Min Act: -0.1700
Data Index: 6869392 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1037. Min Range: -5.1037
Max Act: 5.0099. Min Act: -0.1700
Data Index: 7205841 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9787. Min Act: -0.1700
Data Index: 1201490 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9474. Min Act: -0.1700
Data Index: 8632015 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9474. Min Act: -0.1700
Data Index: 3015426 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9474. Min Act: -0.1700
Data Index: 3438629 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9474. Min Act: -0.1700
Data Index: 538065 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9162. Min Act: -0.1700
Data Index: 5813733 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9162. Min Act: -0.1700
Data Index: 8551040 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9162. Min Act: -0.1700
Data Index: 858281 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9162. Min Act: -0.1700
Data Index: 6757734 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9162. Min Act: -0.1700
Data Index: 2033434 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.9162. Min Act: -0.1700
Data Index: 3299860 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.8849. Min Act: -0.1700
Data Index: 5228658 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.8849. Min Act: -0.1700
Data Index: 2863687 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.8849. Min Act: -0.1700
Data Index: 8439789 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1037. Min Range: -5.1037
Max Act: 4.8849. Min Act: -0.1700
Data Index: 4608870 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19