Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6393 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1643. Min Range: -6.1643
Max Act: 6.1643. Min Act: -0.1700
Data Index: 5874115 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1643. Min Range: -6.1643
Max Act: 6.1018. Min Act: -0.1700
Data Index: 8298270 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1643. Min Range: -6.1643
Max Act: 6.0706. Min Act: -0.1700
Data Index: 8591591 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1643. Min Range: -6.1643
Max Act: 6.0706. Min Act: -0.1700
Data Index: 5039941 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.9768. Min Act: -0.1700
Data Index: 6293106 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.9143. Min Act: -0.1700
Data Index: 1563356 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.9143. Min Act: -0.1700
Data Index: 3512763 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.9143. Min Act: -0.1700
Data Index: 1773982 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.8831. Min Act: -0.1700
Data Index: 7044413 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.8206. Min Act: -0.1700
Data Index: 6047803 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.8206. Min Act: -0.1700
Data Index: 5327929 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.8206. Min Act: -0.1700
Data Index: 1915946 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.7893. Min Act: -0.1700
Data Index: 8463000 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.7893. Min Act: -0.1700
Data Index: 8217991 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.7893. Min Act: -0.1700
Data Index: 5353430 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.7581. Min Act: -0.1700
Data Index: 5253944 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.7581. Min Act: -0.1700
Data Index: 7896478 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.7581. Min Act: -0.1700
Data Index: 8236907 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.6956. Min Act: -0.1700
Data Index: 2699460 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1643. Min Range: -6.1643
Max Act: 5.7268. Min Act: -0.1700
Data Index: 2974347 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19