Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2514 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.6279. Min Act: -0.1700
Data Index: 1609581 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.5342. Min Act: -0.1700
Data Index: 1718078 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.5342. Min Act: -0.1700
Data Index: 518498 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.4717. Min Act: -0.1700
Data Index: 5397502 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.2842. Min Act: -0.1700
Data Index: 5397495 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.2529. Min Act: -0.1700
Data Index: 1826501 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.1904. Min Act: -0.1700
Data Index: 5097071 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.1592. Min Act: -0.1700
Data Index: 1678551 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.1279. Min Act: -0.1700
Data Index: 712784 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.1279. Min Act: -0.1700
Data Index: 4167994 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6279. Min Range: -7.6279
Max Act: 7.0654. Min Act: -0.1700
Data Index: 8196098 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6279. Min Range: -7.6279
Max Act: 6.9717. Min Act: -0.1700
Data Index: 8637024 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6279. Min Range: -7.6279
Max Act: 6.9404. Min Act: -0.1700
Data Index: 6913433 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6279. Min Range: -7.6279
Max Act: 6.8779. Min Act: -0.1700
Data Index: 5397491 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6279. Min Range: -7.6279
Max Act: 6.8779. Min Act: -0.1700
Data Index: 4492611 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6279. Min Range: -7.6279
Max Act: 6.8779. Min Act: -0.1700
Data Index: 7050769 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6279. Min Range: -7.6279
Max Act: 6.7842. Min Act: -0.1700
Data Index: 6295737 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6279. Min Range: -7.6279
Max Act: 6.6904. Min Act: -0.1700
Data Index: 6243546 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6279. Min Range: -7.6279
Max Act: 6.6592. Min Act: -0.1700
Data Index: 3984748 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6279. Min Range: -7.6279
Max Act: 6.6279. Min Act: -0.1700
Data Index: 6295734 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19