Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6366 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 27.4384. Min Range: -27.4384
Max Act: 27.4384. Min Act: -0.1700
Data Index: 5660050 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 27.4384. Min Range: -27.4384
Max Act: 27.3134. Min Act: -0.1700
Data Index: 5122515 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 27.4384. Min Range: -27.4384
Max Act: 27.3134. Min Act: -0.1700
Data Index: 4351797 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 27.4384. Min Range: -27.4384
Max Act: 27.3134. Min Act: -0.1700
Data Index: 3721891 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 27.4384. Min Range: -27.4384
Max Act: 27.3134. Min Act: -0.1700
Data Index: 3437246 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 27.4384. Min Range: -27.4384
Max Act: 27.1884. Min Act: -0.1700
Data Index: 5011144 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.9384. Min Act: -0.1700
Data Index: 3630691 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 27.4384. Min Range: -27.4384
Max Act: 27.0634. Min Act: -0.1700
Data Index: 7049905 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 27.4384. Min Range: -27.4384
Max Act: 27.0634. Min Act: -0.1700
Data Index: 5872083 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.9384. Min Act: -0.1700
Data Index: 5641843 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.9384. Min Act: -0.1700
Data Index: 5780363 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.8134. Min Act: -0.1700
Data Index: 4212033 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.8134. Min Act: -0.1700
Data Index: 6741636 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.8134. Min Act: -0.1700
Data Index: 4030999 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.8134. Min Act: -0.1700
Data Index: 5886510 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.8134. Min Act: -0.1700
Data Index: 783043 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.8134. Min Act: -0.1700
Data Index: 4832600 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.8134. Min Act: -0.1700
Data Index: 4670074 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.8134. Min Act: -0.1700
Data Index: 2319745 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 27.4384. Min Range: -27.4384
Max Act: 26.8134. Min Act: -0.1700
Data Index: 4235500 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19