Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2429 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0093. Min Range: -8.0093
Max Act: 8.0093. Min Act: -0.1700
Data Index: 4884222 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.8843. Min Act: -0.1700
Data Index: 5241380 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.8843. Min Act: -0.1700
Data Index: 1528042 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.8218. Min Act: -0.1700
Data Index: 7428760 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.7593. Min Act: -0.1700
Data Index: 4471149 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.7593. Min Act: -0.1700
Data Index: 5452667 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.6968. Min Act: -0.1700
Data Index: 4416976 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.6968. Min Act: -0.1700
Data Index: 3786806 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.6968. Min Act: -0.1700
Data Index: 932771 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.6343. Min Act: -0.1700
Data Index: 7418855 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.6343. Min Act: -0.1700
Data Index: 5038080 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.5718. Min Act: -0.1700
Data Index: 1501199 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.5718. Min Act: -0.1700
Data Index: 1368988 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.5406. Min Act: -0.1700
Data Index: 7984385 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.5406. Min Act: -0.1700
Data Index: 3812942 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.4781. Min Act: -0.1700
Data Index: 5710838 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.4781. Min Act: -0.1700
Data Index: 5980911 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.4781. Min Act: -0.1700
Data Index: 7448573 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.4781. Min Act: -0.1700
Data Index: 3804829 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0093. Min Range: -8.0093
Max Act: 7.4781. Min Act: -0.1700
Data Index: 1988259 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19