Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.8874. Min Act: -0.1700
Data Index: 887690 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.6061. Min Act: -0.1700
Data Index: 7300312 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.5124. Min Act: -0.1700
Data Index: 5688952 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.3561. Min Act: -0.1700
Data Index: 221977 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.3561. Min Act: -0.1700
Data Index: 5136803 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.3249. Min Act: -0.1700
Data Index: 4619656 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.3249. Min Act: -0.1700
Data Index: 7308891 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.2624. Min Act: -0.1700
Data Index: 6060122 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.2624. Min Act: -0.1700
Data Index: 6835148 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.2624. Min Act: -0.1700
Data Index: 8663281 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.2311. Min Act: -0.1700
Data Index: 7707265 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.2311. Min Act: -0.1700
Data Index: 284308 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.1999. Min Act: -0.1700
Data Index: 1050760 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.1686. Min Act: -0.1700
Data Index: 581665 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.1374. Min Act: -0.1700
Data Index: 7399892 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.1374. Min Act: -0.1700
Data Index: 7094582 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.1374. Min Act: -0.1700
Data Index: 5330035 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.1374. Min Act: -0.1700
Data Index: 1188478 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.1061. Min Act: -0.1700
Data Index: 1522240 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8874. Min Range: -6.8874
Max Act: 6.0749. Min Act: -0.1700
Data Index: 5023634 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19