Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2801 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4648. Min Range: -7.4648
Max Act: 7.4648. Min Act: -0.1700
Data Index: 998823 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4648. Min Range: -7.4648
Max Act: 7.4335. Min Act: -0.1700
Data Index: 775401 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4648. Min Range: -7.4648
Max Act: 7.0273. Min Act: -0.1700
Data Index: 3563387 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.9960. Min Act: -0.1700
Data Index: 3211062 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.9335. Min Act: -0.1700
Data Index: 775399 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.8710. Min Act: -0.1700
Data Index: 20304 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.8710. Min Act: -0.1700
Data Index: 7965757 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.8398. Min Act: -0.1700
Data Index: 5372265 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.8085. Min Act: -0.1700
Data Index: 2875686 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.7773. Min Act: -0.1700
Data Index: 3463442 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.7460. Min Act: -0.1700
Data Index: 5756544 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.7460. Min Act: -0.1700
Data Index: 1653078 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.7773. Min Act: -0.1700
Data Index: 5990042 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.7460. Min Act: -0.1700
Data Index: 5756541 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.7460. Min Act: -0.1700
Data Index: 5756543 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.7460. Min Act: -0.1700
Data Index: 2504603 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.7148. Min Act: -0.1700
Data Index: 5756547 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.6835. Min Act: -0.1700
Data Index: 7094357 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.6523. Min Act: -0.1700
Data Index: 2824870 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4648. Min Range: -7.4648
Max Act: 6.6523. Min Act: -0.1700
Data Index: 6366737 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19