Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2902 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.3633. Min Act: -0.1700
Data Index: 8500901 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1446. Min Act: -0.1700
Data Index: 1488909 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1446. Min Act: -0.1700
Data Index: 6492888 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.0508. Min Act: -0.1700
Data Index: 1796538 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.8633. Min Act: -0.1700
Data Index: 5245126 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.8321. Min Act: -0.1700
Data Index: 7652230 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.8321. Min Act: -0.1700
Data Index: 6003042 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.8008. Min Act: -0.1700
Data Index: 3968711 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.8008. Min Act: -0.1700
Data Index: 6851398 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.7696. Min Act: -0.1700
Data Index: 1510600 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.8008. Min Act: -0.1700
Data Index: 5048127 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.8008. Min Act: -0.1700
Data Index: 2810607 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.7696. Min Act: -0.1700
Data Index: 6492889 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.7383. Min Act: -0.1700
Data Index: 907698 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.7071. Min Act: -0.1700
Data Index: 2685601 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.7071. Min Act: -0.1700
Data Index: 6258850 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.7071. Min Act: -0.1700
Data Index: 2480903 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.7383. Min Act: -0.1700
Data Index: 7303432 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.6758. Min Act: -0.1700
Data Index: 1691370 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3633. Min Range: -7.3633
Max Act: 6.6758. Min Act: -0.1700
Data Index: 516178 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19