Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1126. Min Range: -6.1126
Max Act: 6.1126. Min Act: -0.1700
Data Index: 3953631 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.9563. Min Act: -0.1700
Data Index: 4838662 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.8938. Min Act: -0.1700
Data Index: 1850960 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.8626. Min Act: -0.1700
Data Index: 4396789 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.7688. Min Act: -0.1700
Data Index: 8065001 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.8001. Min Act: -0.1700
Data Index: 2753027 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.7688. Min Act: -0.1700
Data Index: 189491 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.6751. Min Act: -0.1700
Data Index: 2263453 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.6438. Min Act: -0.1700
Data Index: 1926865 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.6126. Min Act: -0.1700
Data Index: 2327705 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.5813. Min Act: -0.1700
Data Index: 3179712 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.5501. Min Act: -0.1700
Data Index: 1389459 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.4876. Min Act: -0.1700
Data Index: 8176246 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.4563. Min Act: -0.1700
Data Index: 2681302 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.4563. Min Act: -0.1700
Data Index: 4754834 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.4563. Min Act: -0.1700
Data Index: 4234768 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.4563. Min Act: -0.1700
Data Index: 7661662 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.4563. Min Act: -0.1700
Data Index: 522261 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.4563. Min Act: -0.1700
Data Index: 1673054 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1126. Min Range: -6.1126
Max Act: 5.3938. Min Act: -0.1700
Data Index: 4549269 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19