Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1290. Min Range: -8.1290
Max Act: 8.1290. Min Act: -0.1700
Data Index: 2986288 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.9415. Min Act: -0.1700
Data Index: 7011479 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.9415. Min Act: -0.1700
Data Index: 5031535 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.8790. Min Act: -0.1700
Data Index: 1214964 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.8790. Min Act: -0.1700
Data Index: 1618344 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.8790. Min Act: -0.1700
Data Index: 6166441 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.8165. Min Act: -0.1700
Data Index: 6893509 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.7540. Min Act: -0.1700
Data Index: 1918866 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.6602. Min Act: -0.1700
Data Index: 1842450 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.6602. Min Act: -0.1700
Data Index: 6620297 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.6290. Min Act: -0.1700
Data Index: 758446 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.6602. Min Act: -0.1700
Data Index: 5061590 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.6602. Min Act: -0.1700
Data Index: 7199802 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.6290. Min Act: -0.1700
Data Index: 4082500 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.5977. Min Act: -0.1700
Data Index: 4265538 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.5665. Min Act: -0.1700
Data Index: 7070248 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.5665. Min Act: -0.1700
Data Index: 5034413 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.5352. Min Act: -0.1700
Data Index: 7091863 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.5352. Min Act: -0.1700
Data Index: 6234568 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1290. Min Range: -8.1290
Max Act: 7.5040. Min Act: -0.1700
Data Index: 5969992 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19