Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1061. Min Range: -9.1061
Max Act: 9.1061. Min Act: -0.1700
Data Index: 2005559 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1061. Min Range: -9.1061
Max Act: 8.3561. Min Act: -0.1700
Data Index: 4661850 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1061. Min Range: -9.1061
Max Act: 8.1686. Min Act: -0.1700
Data Index: 6026405 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1061. Min Range: -9.1061
Max Act: 8.1061. Min Act: -0.1700
Data Index: 1278987 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.9811. Min Act: -0.1700
Data Index: 4826729 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1061. Min Range: -9.1061
Max Act: 8.0436. Min Act: -0.1700
Data Index: 3050650 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1061. Min Range: -9.1061
Max Act: 8.0436. Min Act: -0.1700
Data Index: 3642954 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.9811. Min Act: -0.1700
Data Index: 8314465 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.9811. Min Act: -0.1700
Data Index: 4404913 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.9811. Min Act: -0.1700
Data Index: 6603659 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.9186. Min Act: -0.1700
Data Index: 5895522 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.9811. Min Act: -0.1700
Data Index: 5040242 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.9186. Min Act: -0.1700
Data Index: 7504950 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.9186. Min Act: -0.1700
Data Index: 8715628 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.9186. Min Act: -0.1700
Data Index: 1555952 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.9186. Min Act: -0.1700
Data Index: 8636035 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.8561. Min Act: -0.1700
Data Index: 410885 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.8561. Min Act: -0.1700
Data Index: 5277319 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.8561. Min Act: -0.1700
Data Index: 2391705 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1061. Min Range: -9.1061
Max Act: 7.8561. Min Act: -0.1700
Data Index: 6798429 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19