Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1240. Min Range: -4.1240
Max Act: 4.1240. Min Act: -0.1700
Data Index: 5200926 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1240. Min Range: -4.1240
Max Act: 4.0927. Min Act: -0.1700
Data Index: 8380426 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1240. Min Range: -4.1240
Max Act: 4.0927. Min Act: -0.1700
Data Index: 6919895 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1240. Min Range: -4.1240
Max Act: 4.0615. Min Act: -0.1700
Data Index: 5115945 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.9677. Min Act: -0.1700
Data Index: 4769995 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.9677. Min Act: -0.1700
Data Index: 8380436 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.9364. Min Act: -0.1700
Data Index: 4370773 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.9364. Min Act: -0.1700
Data Index: 5288549 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.9364. Min Act: -0.1700
Data Index: 5927854 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.9364. Min Act: -0.1700
Data Index: 1236867 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.9052. Min Act: -0.1700
Data Index: 1551853 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.8739. Min Act: -0.1700
Data Index: 7252455 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.8739. Min Act: -0.1700
Data Index: 8547900 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.8426. Min Act: -0.1700
Data Index: 1573819 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.8426. Min Act: -0.1700
Data Index: 2447355 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.8426. Min Act: -0.1700
Data Index: 4675461 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.8113. Min Act: -0.1700
Data Index: 6457041 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.8113. Min Act: -0.1700
Data Index: 6494807 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.8113. Min Act: -0.1700
Data Index: 793664 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1240. Min Range: -4.1240
Max Act: 3.8113. Min Act: -0.1700
Data Index: 743084 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19