Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5286 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3662. Min Range: -6.3662
Max Act: 6.3662. Min Act: -0.1700
Data Index: 2663205 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.9287. Min Act: -0.1700
Data Index: 6090141 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.8975. Min Act: -0.1700
Data Index: 4776739 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.8975. Min Act: -0.1700
Data Index: 3746001 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.8975. Min Act: -0.1700
Data Index: 1572543 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.8662. Min Act: -0.1700
Data Index: 1200552 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.8350. Min Act: -0.1700
Data Index: 6140345 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.8037. Min Act: -0.1700
Data Index: 7098668 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.7412. Min Act: -0.1700
Data Index: 1859044 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.7412. Min Act: -0.1700
Data Index: 5545847 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.7100. Min Act: -0.1700
Data Index: 4724446 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.6787. Min Act: -0.1700
Data Index: 1786102 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.6475. Min Act: -0.1700
Data Index: 5179367 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.6787. Min Act: -0.1700
Data Index: 8168065 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.6475. Min Act: -0.1700
Data Index: 5881782 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.6475. Min Act: -0.1700
Data Index: 4248466 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.6162. Min Act: -0.1700
Data Index: 5775083 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.5850. Min Act: -0.1700
Data Index: 3616161 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.5850. Min Act: -0.1700
Data Index: 6337229 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3662. Min Range: -6.3662
Max Act: 5.5537. Min Act: -0.1700
Data Index: 1348468 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19