Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4713 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.5869. Min Act: -0.1700
Data Index: 759378 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.4303. Min Act: -0.1700
Data Index: 2647214 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.3833. Min Act: -0.1700
Data Index: 6327675 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.3989. Min Act: -0.1700
Data Index: 7927483 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.3989. Min Act: -0.1700
Data Index: 4207473 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.3833. Min Act: -0.1700
Data Index: 5912135 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.3833. Min Act: -0.1700
Data Index: 939174 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.3519. Min Act: -0.1700
Data Index: 4075834 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.3048. Min Act: -0.1700
Data Index: 5318839 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.2734. Min Act: -0.1700
Data Index: 4839920 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.2420. Min Act: -0.1700
Data Index: 4549944 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.2734. Min Act: -0.1700
Data Index: 6986610 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.2420. Min Act: -0.1700
Data Index: 1884063 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.2420. Min Act: -0.1700
Data Index: 5841834 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.2420. Min Act: -0.1700
Data Index: 8669699 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.2106. Min Act: -0.1700
Data Index: 8604135 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.1791. Min Act: -0.1700
Data Index: 6986039 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.1948. Min Act: -0.1700
Data Index: 2729009 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.1791. Min Act: -0.1700
Data Index: 4726777 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5869. Min Range: -3.5869
Max Act: 3.1791. Min Act: -0.1700
Data Index: 3707128 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19