Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4347 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.5565. Min Act: -0.1700
Data Index: 8014296 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.3690. Min Act: -0.1700
Data Index: 8449930 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.3377. Min Act: -0.1700
Data Index: 4927701 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.3065. Min Act: -0.1700
Data Index: 6137389 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.2752. Min Act: -0.1700
Data Index: 4826683 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.2127. Min Act: -0.1700
Data Index: 8333404 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.1815. Min Act: -0.1700
Data Index: 3114699 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.2127. Min Act: -0.1700
Data Index: 6219917 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.1502. Min Act: -0.1700
Data Index: 1673554 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.0877. Min Act: -0.1700
Data Index: 3119220 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.0877. Min Act: -0.1700
Data Index: 6402514 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.0877. Min Act: -0.1700
Data Index: 114586 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.0877. Min Act: -0.1700
Data Index: 1866225 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.0252. Min Act: -0.1700
Data Index: 5436250 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.0252. Min Act: -0.1700
Data Index: 2463308 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5565. Min Range: -6.5565
Max Act: 5.9940. Min Act: -0.1700
Data Index: 4955444 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.0252. Min Act: -0.1700
Data Index: 8577709 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.0252. Min Act: -0.1700
Data Index: 5862684 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.0252. Min Act: -0.1700
Data Index: 1806458 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5565. Min Range: -6.5565
Max Act: 6.0252. Min Act: -0.1700
Data Index: 155437 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19