Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2467 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.8653. Min Act: -0.1700
Data Index: 571837 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.8340. Min Act: -0.1700
Data Index: 7945961 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.8340. Min Act: -0.1700
Data Index: 8777401 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.8028. Min Act: -0.1700
Data Index: 288602 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.7715. Min Act: -0.1700
Data Index: 3090922 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.7403. Min Act: -0.1700
Data Index: 3450824 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.7403. Min Act: -0.1700
Data Index: 4485751 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.7403. Min Act: -0.1700
Data Index: 4221540 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.7403. Min Act: -0.1700
Data Index: 4300318 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.7090. Min Act: -0.1700
Data Index: 3427612 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.7090. Min Act: -0.1700
Data Index: 8260863 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.6778. Min Act: -0.1700
Data Index: 8336118 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.6778. Min Act: -0.1700
Data Index: 73862 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.6778. Min Act: -0.1700
Data Index: 1480356 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.6465. Min Act: -0.1700
Data Index: 5280360 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.6465. Min Act: -0.1700
Data Index: 5539171 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.6465. Min Act: -0.1700
Data Index: 8798409 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.6465. Min Act: -0.1700
Data Index: 8253848 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.6153. Min Act: -0.1700
Data Index: 5908457 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8653. Min Range: -4.8653
Max Act: 4.6153. Min Act: -0.1700
Data Index: 3702692 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19