Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2113 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6010. Min Range: -8.6010
Max Act: 8.6010. Min Act: -0.1700
Data Index: 6515965 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6010. Min Range: -8.6010
Max Act: 8.4760. Min Act: -0.1700
Data Index: 3513481 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6010. Min Range: -8.6010
Max Act: 8.1322. Min Act: -0.1700
Data Index: 4237098 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6010. Min Range: -8.6010
Max Act: 8.0697. Min Act: -0.1700
Data Index: 266211 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6010. Min Range: -8.6010
Max Act: 8.1010. Min Act: -0.1700
Data Index: 1018796 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6010. Min Range: -8.6010
Max Act: 8.0072. Min Act: -0.1700
Data Index: 6326099 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.9760. Min Act: -0.1700
Data Index: 5573136 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.9135. Min Act: -0.1700
Data Index: 8088121 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.8822. Min Act: -0.1700
Data Index: 8548041 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.8510. Min Act: -0.1700
Data Index: 5124295 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.8197. Min Act: -0.1700
Data Index: 2876235 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.8197. Min Act: -0.1700
Data Index: 6446271 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.7885. Min Act: -0.1700
Data Index: 7108628 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.6947. Min Act: -0.1700
Data Index: 1694828 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.6947. Min Act: -0.1700
Data Index: 2991572 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.7260. Min Act: -0.1700
Data Index: 961367 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.6947. Min Act: -0.1700
Data Index: 1417186 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.6635. Min Act: -0.1700
Data Index: 4545669 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.6635. Min Act: -0.1700
Data Index: 5285968 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6010. Min Range: -8.6010
Max Act: 7.6322. Min Act: -0.1700
Data Index: 2215903 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19