Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4521 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.9998. Min Act: -0.1700
Data Index: 1995309 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.9479. Min Act: -0.1700
Data Index: 2174912 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.8879. Min Act: -0.1700
Data Index: 7245695 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.8708. Min Act: -0.1700
Data Index: 2641750 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.8538. Min Act: -0.1700
Data Index: 4938559 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.8454. Min Act: -0.1699
Data Index: 8524174 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.8538. Min Act: -0.1700
Data Index: 862956 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7948. Min Act: -0.1697
Data Index: 1225065 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7865. Min Act: -0.1698
Data Index: 8309007 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7948. Min Act: -0.1700
Data Index: 1739646 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7865. Min Act: -0.1700
Data Index: 7907666 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7698. Min Act: -0.1700
Data Index: 2546391 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7615. Min Act: -0.1700
Data Index: 2869234 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7449. Min Act: -0.1700
Data Index: 2039019 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7366. Min Act: -0.1700
Data Index: 3765964 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7366. Min Act: -0.1699
Data Index: 672272 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7202. Min Act: -0.1700
Data Index: 7827835 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7202. Min Act: -0.1700
Data Index: 6899089 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7202. Min Act: -0.1699
Data Index: 749547 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9998. Min Range: -0.9998
Max Act: 0.7038. Min Act: -0.1700
Data Index: 5637741 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19