Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 305 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9427. Min Range: -11.9427
Max Act: 11.9427. Min Act: -0.1700
Data Index: 8260164 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9427. Min Range: -11.9427
Max Act: 11.8177. Min Act: -0.1700
Data Index: 5145526 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9427. Min Range: -11.9427
Max Act: 11.1927. Min Act: -0.1700
Data Index: 4149830 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9427. Min Range: -11.9427
Max Act: 11.0052. Min Act: -0.1700
Data Index: 3637762 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9427. Min Range: -11.9427
Max Act: 11.0052. Min Act: -0.1700
Data Index: 7891218 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9427. Min Range: -11.9427
Max Act: 11.0052. Min Act: -0.1700
Data Index: 2119070 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9427. Min Range: -11.9427
Max Act: 11.0052. Min Act: -0.1700
Data Index: 5969625 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.9427. Min Act: -0.1700
Data Index: 5183612 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.9427. Min Act: -0.1700
Data Index: 500150 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.9427. Min Act: -0.1700
Data Index: 399841 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9427. Min Range: -11.9427
Max Act: 11.0052. Min Act: -0.1700
Data Index: 4149829 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.8802. Min Act: -0.1700
Data Index: 7418464 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.8802. Min Act: -0.1700
Data Index: 1602668 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.8177. Min Act: -0.1700
Data Index: 1784725 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.7552. Min Act: -0.1700
Data Index: 5354570 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.8177. Min Act: -0.1700
Data Index: 5470675 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.8177. Min Act: -0.1700
Data Index: 4691881 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.6927. Min Act: -0.1700
Data Index: 2338047 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.7552. Min Act: -0.1700
Data Index: 6722545 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9427. Min Range: -11.9427
Max Act: 10.6927. Min Act: -0.1700
Data Index: 6530199 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19