Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2349 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0187. Min Range: -3.0187
Max Act: 3.0187. Min Act: -0.1700
Data Index: 349600 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0187. Min Range: -3.0187
Max Act: 3.0029. Min Act: -0.1700
Data Index: 4052618 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.9396. Min Act: -0.1700
Data Index: 314181 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.9396. Min Act: -0.1700
Data Index: 3937989 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.9396. Min Act: -0.1700
Data Index: 2317948 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.9079. Min Act: -0.1700
Data Index: 2155512 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8444. Min Act: -0.1700
Data Index: 4467893 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8444. Min Act: -0.1700
Data Index: 7401147 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8285. Min Act: -0.1700
Data Index: 7117729 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8285. Min Act: -0.1700
Data Index: 5528016 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8444. Min Act: -0.1700
Data Index: 4904095 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8126. Min Act: -0.1700
Data Index: 3040692 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7967. Min Act: -0.1700
Data Index: 1453733 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8126. Min Act: -0.1700
Data Index: 5993137 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8126. Min Act: -0.1700
Data Index: 2416201 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7967. Min Act: -0.1700
Data Index: 7795598 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7967. Min Act: -0.1700
Data Index: 4718849 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7967. Min Act: -0.1700
Data Index: 1507772 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7967. Min Act: -0.1700
Data Index: 4643360 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7967. Min Act: -0.1700
Data Index: 5608479 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19