Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4822 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1524. Min Range: -5.1524
Max Act: 5.1524. Min Act: -0.1700
Data Index: 8216571 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1524. Min Range: -5.1524
Max Act: 5.1524. Min Act: -0.1700
Data Index: 7226623 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1524. Min Range: -5.1524
Max Act: 5.1211. Min Act: -0.1700
Data Index: 1716936 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.9961. Min Act: -0.1700
Data Index: 6552948 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.9649. Min Act: -0.1700
Data Index: 7183280 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.9024. Min Act: -0.1700
Data Index: 3732195 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.9024. Min Act: -0.1700
Data Index: 1807810 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.8711. Min Act: -0.1700
Data Index: 1963484 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.8086. Min Act: -0.1700
Data Index: 5969472 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7774. Min Act: -0.1700
Data Index: 6981476 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7461. Min Act: -0.1700
Data Index: 6676577 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7461. Min Act: -0.1700
Data Index: 5642635 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7149. Min Act: -0.1700
Data Index: 2555484 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7149. Min Act: -0.1700
Data Index: 7470517 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7149. Min Act: -0.1700
Data Index: 7269390 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.6524. Min Act: -0.1700
Data Index: 6568584 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.6524. Min Act: -0.1700
Data Index: 5326666 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.6524. Min Act: -0.1700
Data Index: 3040696 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.6524. Min Act: -0.1700
Data Index: 4591212 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.6524. Min Act: -0.1700
Data Index: 6138797 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19