Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2896. Min Range: -8.2896
Max Act: 8.2896. Min Act: -0.1700
Data Index: 3924676 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2896. Min Range: -8.2896
Max Act: 8.1021. Min Act: -0.1700
Data Index: 3117470 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2896. Min Range: -8.2896
Max Act: 8.0396. Min Act: -0.1700
Data Index: 444334 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2896. Min Range: -8.2896
Max Act: 8.0396. Min Act: -0.1700
Data Index: 3209637 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2896. Min Range: -8.2896
Max Act: 8.0396. Min Act: -0.1700
Data Index: 3913786 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.9771. Min Act: -0.1700
Data Index: 4194084 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.9146. Min Act: -0.1700
Data Index: 385266 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.8521. Min Act: -0.1700
Data Index: 2694034 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.9146. Min Act: -0.1700
Data Index: 8784766 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.8521. Min Act: -0.1700
Data Index: 6833769 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.8521. Min Act: -0.1700
Data Index: 8708025 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.7896. Min Act: -0.1700
Data Index: 4750330 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.7896. Min Act: -0.1700
Data Index: 6347162 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.7896. Min Act: -0.1700
Data Index: 5695330 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.7271. Min Act: -0.1700
Data Index: 3027181 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.7896. Min Act: -0.1700
Data Index: 697785 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.7896. Min Act: -0.1700
Data Index: 5803342 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.7271. Min Act: -0.1700
Data Index: 4638778 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.7271. Min Act: -0.1700
Data Index: 7533825 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2896. Min Range: -8.2896
Max Act: 7.6646. Min Act: -0.1700
Data Index: 2932032 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19