Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 504 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3452. Min Range: -7.3452
Max Act: 7.3452. Min Act: -0.1700
Data Index: 4377891 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3452. Min Range: -7.3452
Max Act: 7.1889. Min Act: -0.1700
Data Index: 1537924 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3452. Min Range: -7.3452
Max Act: 7.1264. Min Act: -0.1700
Data Index: 1709611 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3452. Min Range: -7.3452
Max Act: 7.0327. Min Act: -0.1700
Data Index: 1522433 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.9077. Min Act: -0.1700
Data Index: 3062277 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.8764. Min Act: -0.1700
Data Index: 8719913 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.8764. Min Act: -0.1700
Data Index: 6496060 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.8452. Min Act: -0.1700
Data Index: 1745691 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.7827. Min Act: -0.1700
Data Index: 1161812 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.7827. Min Act: -0.1700
Data Index: 4536031 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.7514. Min Act: -0.1700
Data Index: 8077891 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.7202. Min Act: -0.1700
Data Index: 6212193 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.6889. Min Act: -0.1700
Data Index: 3461940 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.6889. Min Act: -0.1700
Data Index: 3694931 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.6577. Min Act: -0.1700
Data Index: 4722698 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.6577. Min Act: -0.1700
Data Index: 2315818 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.6577. Min Act: -0.1700
Data Index: 8323723 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.6577. Min Act: -0.1700
Data Index: 296768 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.6264. Min Act: -0.1700
Data Index: 2534998 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3452. Min Range: -7.3452
Max Act: 6.5952. Min Act: -0.1700
Data Index: 8257611 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19