Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 445 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.1690. Min Act: -0.1700
Data Index: 5068 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.1690. Min Act: -0.1700
Data Index: 7573424 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.1377. Min Act: -0.1700
Data Index: 3850141 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.1065. Min Act: -0.1700
Data Index: 4962915 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.1065. Min Act: -0.1700
Data Index: 5536862 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0752. Min Act: -0.1700
Data Index: 7509340 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0752. Min Act: -0.1700
Data Index: 337478 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0440. Min Act: -0.1700
Data Index: 7518555 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0440. Min Act: -0.1700
Data Index: 2429913 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0440. Min Act: -0.1700
Data Index: 7365262 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0440. Min Act: -0.1700
Data Index: 7248690 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0127. Min Act: -0.1700
Data Index: 7926245 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0127. Min Act: -0.1700
Data Index: 1089730 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0127. Min Act: -0.1700
Data Index: 5216128 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0127. Min Act: -0.1700
Data Index: 6871464 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1690. Min Range: -5.1690
Max Act: 5.0127. Min Act: -0.1700
Data Index: 7248689 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1690. Min Range: -5.1690
Max Act: 4.9815. Min Act: -0.1700
Data Index: 3216047 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1690. Min Range: -5.1690
Max Act: 4.9815. Min Act: -0.1700
Data Index: 2118848 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1690. Min Range: -5.1690
Max Act: 4.9815. Min Act: -0.1700
Data Index: 1319536 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1690. Min Range: -5.1690
Max Act: 4.9502. Min Act: -0.1700
Data Index: 4082884 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19