Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 130 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.3245. Min Act: -0.1700
Data Index: 2440526 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.1682. Min Act: -0.1700
Data Index: 3928817 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.1370. Min Act: -0.1700
Data Index: 5489457 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.0432. Min Act: -0.1700
Data Index: 7246583 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.0120. Min Act: -0.1700
Data Index: 5661630 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9807. Min Act: -0.1700
Data Index: 872586 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9807. Min Act: -0.1700
Data Index: 6446033 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9495. Min Act: -0.1700
Data Index: 16153 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9182. Min Act: -0.1700
Data Index: 5312634 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.8870. Min Act: -0.1700
Data Index: 6689530 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.8870. Min Act: -0.1700
Data Index: 3684743 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.8870. Min Act: -0.1700
Data Index: 3821537 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.8557. Min Act: -0.1700
Data Index: 4616699 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.8245. Min Act: -0.1700
Data Index: 3051174 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.8557. Min Act: -0.1700
Data Index: 2977314 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.8557. Min Act: -0.1700
Data Index: 1100747 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.8557. Min Act: -0.1700
Data Index: 2911524 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.7932. Min Act: -0.1700
Data Index: 4090945 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.7932. Min Act: -0.1700
Data Index: 8469530 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.7620. Min Act: -0.1700
Data Index: 6982493 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19