Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1552. Min Range: -7.1552
Max Act: 7.1552. Min Act: -0.1700
Data Index: 7057546 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1552. Min Range: -7.1552
Max Act: 7.0927. Min Act: -0.1700
Data Index: 5564830 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1552. Min Range: -7.1552
Max Act: 7.0615. Min Act: -0.1700
Data Index: 6379398 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.9990. Min Act: -0.1700
Data Index: 2206180 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.9677. Min Act: -0.1699
Data Index: 3374771 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.9052. Min Act: -0.1700
Data Index: 7048895 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.9052. Min Act: -0.1700
Data Index: 4034048 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.8427. Min Act: -0.1700
Data Index: 1714024 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.8427. Min Act: -0.1700
Data Index: 5160006 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.8427. Min Act: -0.1700
Data Index: 2398987 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.8115. Min Act: -0.1700
Data Index: 1057437 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.8115. Min Act: -0.1700
Data Index: 2419913 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.8115. Min Act: -0.1700
Data Index: 6541133 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.8115. Min Act: -0.1700
Data Index: 8695305 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.8115. Min Act: -0.1700
Data Index: 6444349 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.8115. Min Act: -0.1700
Data Index: 687152 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.7802. Min Act: -0.1700
Data Index: 973364 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.7490. Min Act: -0.1700
Data Index: 7425004 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.7177. Min Act: -0.1700
Data Index: 7645605 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1552. Min Range: -7.1552
Max Act: 6.7177. Min Act: -0.1700
Data Index: 6209013 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19