Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6224 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.4982. Min Act: -0.1700
Data Index: 4019647 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.5607. Min Act: -0.1700
Data Index: 8371611 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.3419. Min Act: -0.1700
Data Index: 1533886 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.2482. Min Act: -0.1700
Data Index: 5687949 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.1857. Min Act: -0.1700
Data Index: 8167301 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.1544. Min Act: -0.1700
Data Index: 8005121 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.1544. Min Act: -0.1700
Data Index: 8024595 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.0919. Min Act: -0.1700
Data Index: 3031075 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.1232. Min Act: -0.1700
Data Index: 2444920 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.0919. Min Act: -0.1700
Data Index: 6645996 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.0294. Min Act: -0.1700
Data Index: 5437 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.0607. Min Act: -0.1700
Data Index: 4732477 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5607. Min Range: -7.5607
Max Act: 7.0294. Min Act: -0.1700
Data Index: 6379565 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5607. Min Range: -7.5607
Max Act: 6.9982. Min Act: -0.1700
Data Index: 1800264 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5607. Min Range: -7.5607
Max Act: 6.9982. Min Act: -0.1700
Data Index: 399996 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5607. Min Range: -7.5607
Max Act: 6.9982. Min Act: -0.1700
Data Index: 5608243 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5607. Min Range: -7.5607
Max Act: 6.9669. Min Act: -0.1700
Data Index: 3133155 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5607. Min Range: -7.5607
Max Act: 6.9669. Min Act: -0.1700
Data Index: 5575451 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5607. Min Range: -7.5607
Max Act: 6.9982. Min Act: -0.1700
Data Index: 5602863 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5607. Min Range: -7.5607
Max Act: 6.9669. Min Act: -0.1700
Data Index: 7527454 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19