Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4333 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.7582. Min Act: -0.1700
Data Index: 3810695 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.6957. Min Act: -0.1700
Data Index: 698840 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.5082. Min Act: -0.1700
Data Index: 8757796 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.4457. Min Act: -0.1700
Data Index: 6407283 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.4145. Min Act: -0.1700
Data Index: 8050793 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.3832. Min Act: -0.1700
Data Index: 2924215 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.3832. Min Act: -0.1700
Data Index: 7264364 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.3520. Min Act: -0.1700
Data Index: 5803848 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.3520. Min Act: -0.1700
Data Index: 1159629 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.3207. Min Act: -0.1700
Data Index: 8640623 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.2895. Min Act: -0.1700
Data Index: 7222225 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.2270. Min Act: -0.1700
Data Index: 1456461 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.2270. Min Act: -0.1700
Data Index: 2049139 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.2270. Min Act: -0.1700
Data Index: 2421692 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.1957. Min Act: -0.1700
Data Index: 5126332 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.1957. Min Act: -0.1700
Data Index: 3949838 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.1957. Min Act: -0.1700
Data Index: 6831314 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.2270. Min Act: -0.1700
Data Index: 3210294 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.1645. Min Act: -0.1700
Data Index: 7025326 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7582. Min Range: -6.7582
Max Act: 6.1645. Min Act: -0.1700
Data Index: 7687632 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19