Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1613 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0625. Min Range: -6.0625
Max Act: 6.0625. Min Act: -0.1700
Data Index: 2113736 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.9063. Min Act: -0.1700
Data Index: 7877003 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.9063. Min Act: -0.1700
Data Index: 3205532 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.8438. Min Act: -0.1700
Data Index: 4665010 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.8125. Min Act: -0.1700
Data Index: 8484352 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.8125. Min Act: -0.1700
Data Index: 2872172 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.8125. Min Act: -0.1700
Data Index: 6109734 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.8438. Min Act: -0.1700
Data Index: 8114804 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.8125. Min Act: -0.1700
Data Index: 6771397 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.7500. Min Act: -0.1700
Data Index: 1067064 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.7500. Min Act: -0.1700
Data Index: 8102554 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.7500. Min Act: -0.1700
Data Index: 4224492 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.7188. Min Act: -0.1700
Data Index: 5311846 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.7188. Min Act: -0.1700
Data Index: 4747585 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.7188. Min Act: -0.1700
Data Index: 8472464 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.7188. Min Act: -0.1699
Data Index: 1374593 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.7500. Min Act: -0.1700
Data Index: 5300333 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.7500. Min Act: -0.1700
Data Index: 5511981 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.7500. Min Act: -0.1700
Data Index: 502581 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0625. Min Range: -6.0625
Max Act: 5.6875. Min Act: -0.1700
Data Index: 3985624 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19