Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2243 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1615. Min Range: -7.1615
Max Act: 7.1615. Min Act: -0.1700
Data Index: 6444438 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1615. Min Range: -7.1615
Max Act: 7.0990. Min Act: -0.1700
Data Index: 1299584 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1615. Min Range: -7.1615
Max Act: 7.0990. Min Act: -0.1700
Data Index: 8738238 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1615. Min Range: -7.1615
Max Act: 7.0677. Min Act: -0.1700
Data Index: 1780447 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1615. Min Range: -7.1615
Max Act: 7.0365. Min Act: -0.1700
Data Index: 4921844 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1615. Min Range: -7.1615
Max Act: 7.0052. Min Act: -0.1700
Data Index: 7221677 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.9115. Min Act: -0.1700
Data Index: 6510728 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.8802. Min Act: -0.1700
Data Index: 5722711 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.8177. Min Act: -0.1700
Data Index: 1351091 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.7552. Min Act: -0.1700
Data Index: 7638169 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.7552. Min Act: -0.1700
Data Index: 4602159 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.7552. Min Act: -0.1700
Data Index: 3739527 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.7240. Min Act: -0.1700
Data Index: 8071252 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.7240. Min Act: -0.1700
Data Index: 5717834 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.6927. Min Act: -0.1700
Data Index: 725423 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.6927. Min Act: -0.1700
Data Index: 2771387 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.6615. Min Act: -0.1700
Data Index: 5372351 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.6927. Min Act: -0.1700
Data Index: 860984 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.6615. Min Act: -0.1700
Data Index: 543501 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1615. Min Range: -7.1615
Max Act: 6.6615. Min Act: -0.1700
Data Index: 5363696 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19