Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1724 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0164. Min Range: -6.0164
Max Act: 6.0164. Min Act: -0.1700
Data Index: 496892 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.9226. Min Act: -0.1700
Data Index: 4660018 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8914. Min Act: -0.1700
Data Index: 2122645 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.9226. Min Act: -0.1700
Data Index: 395148 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8601. Min Act: -0.1700
Data Index: 3852990 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8289. Min Act: -0.1700
Data Index: 2427611 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.7976. Min Act: -0.1700
Data Index: 8364910 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.7976. Min Act: -0.1700
Data Index: 7879623 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.7664. Min Act: -0.1700
Data Index: 2689087 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.7664. Min Act: -0.1700
Data Index: 153169 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.7351. Min Act: -0.1700
Data Index: 1803319 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.7039. Min Act: -0.1700
Data Index: 4775877 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.6726. Min Act: -0.1700
Data Index: 3952074 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.6726. Min Act: -0.1700
Data Index: 565862 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.6101. Min Act: -0.1700
Data Index: 7360627 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.6414. Min Act: -0.1700
Data Index: 4094935 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.6414. Min Act: -0.1700
Data Index: 100236 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.5789. Min Act: -0.1700
Data Index: 1125034 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.6101. Min Act: -0.1700
Data Index: 6543668 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.5789. Min Act: -0.1700
Data Index: 758406 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19