Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2714 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.8387. Min Act: -0.1700
Data Index: 8707964 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.5887. Min Act: -0.1700
Data Index: 280850 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.4637. Min Act: -0.1700
Data Index: 5400154 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.4012. Min Act: -0.1700
Data Index: 4503738 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0887. Min Act: -0.1700
Data Index: 1335136 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.2137. Min Act: -0.1700
Data Index: 2017820 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.1512. Min Act: -0.1700
Data Index: 4226723 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.1512. Min Act: -0.1700
Data Index: 5370125 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.1512. Min Act: -0.1700
Data Index: 6409674 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0262. Min Act: -0.1700
Data Index: 3766425 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0887. Min Act: -0.1700
Data Index: 985931 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0887. Min Act: -0.1700
Data Index: 88159 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0887. Min Act: -0.1700
Data Index: 2500283 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0262. Min Act: -0.1700
Data Index: 2839398 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0887. Min Act: -0.1700
Data Index: 5393869 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0262. Min Act: -0.1700
Data Index: 3197168 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0262. Min Act: -0.1700
Data Index: 5818866 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0262. Min Act: -0.1700
Data Index: 5328696 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8387. Min Range: -11.8387
Max Act: 11.0262. Min Act: -0.1700
Data Index: 6053472 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8387. Min Range: -11.8387
Max Act: 10.9637. Min Act: -0.1700
Data Index: 3617986 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19