Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 916 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.6000. Min Act: -0.1700
Data Index: 8681734 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.6000. Min Act: -0.1700
Data Index: 1573173 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.3500. Min Act: -0.1700
Data Index: 4256912 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.2250. Min Act: -0.1700
Data Index: 4634851 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.2250. Min Act: -0.1700
Data Index: 2520168 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.1625. Min Act: -0.1700
Data Index: 5097170 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.1625. Min Act: -0.1700
Data Index: 8467992 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.1625. Min Act: -0.1700
Data Index: 6504971 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.1625. Min Act: -0.1700
Data Index: 7564459 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.1000. Min Act: -0.1700
Data Index: 2366894 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.1000. Min Act: -0.1700
Data Index: 1402999 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.0375. Min Act: -0.1700
Data Index: 4832591 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.0375. Min Act: -0.1700
Data Index: 7700391 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.0375. Min Act: -0.1700
Data Index: 3928099 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.0375. Min Act: -0.1700
Data Index: 6735217 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6000. Min Range: -8.6000
Max Act: 7.9750. Min Act: -0.1700
Data Index: 4234801 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6000. Min Range: -8.6000
Max Act: 8.0375. Min Act: -0.1700
Data Index: 7943493 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6000. Min Range: -8.6000
Max Act: 7.9750. Min Act: -0.1700
Data Index: 1353198 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6000. Min Range: -8.6000
Max Act: 7.9750. Min Act: -0.1700
Data Index: 5990577 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6000. Min Range: -8.6000
Max Act: 7.9750. Min Act: -0.1700
Data Index: 3329068 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19