Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1447. Min Range: -7.1447
Max Act: 7.1447. Min Act: -0.1700
Data Index: 1457702 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.8947. Min Act: -0.1700
Data Index: 6525699 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.8947. Min Act: -0.1700
Data Index: 8732782 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.8947. Min Act: -0.1700
Data Index: 598252 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.8634. Min Act: -0.1700
Data Index: 3816970 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.8009. Min Act: -0.1700
Data Index: 1319544 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.8009. Min Act: -0.1700
Data Index: 4730615 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.7697. Min Act: -0.1700
Data Index: 4105425 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.7384. Min Act: -0.1700
Data Index: 7996328 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.7072. Min Act: -0.1700
Data Index: 1663481 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.7072. Min Act: -0.1700
Data Index: 1110550 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.6759. Min Act: -0.1700
Data Index: 4933538 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.6759. Min Act: -0.1700
Data Index: 7908827 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.6134. Min Act: -0.1700
Data Index: 2868555 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.6447. Min Act: -0.1700
Data Index: 1734933 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.6447. Min Act: -0.1700
Data Index: 2108451 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.6447. Min Act: -0.1700
Data Index: 4829966 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.6447. Min Act: -0.1700
Data Index: 1288911 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.6134. Min Act: -0.1700
Data Index: 381461 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1447. Min Range: -7.1447
Max Act: 6.6134. Min Act: -0.1700
Data Index: 1150016 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19