Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.8452. Min Act: -0.1700
Data Index: 7530191 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5327. Min Act: -0.1700
Data Index: 4036247 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5327. Min Act: -0.1700
Data Index: 3725210 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5015. Min Act: -0.1700
Data Index: 1877859 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.5015. Min Act: -0.1700
Data Index: 701245 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.4702. Min Act: -0.1700
Data Index: 2680066 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.4702. Min Act: -0.1700
Data Index: 6543172 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.4077. Min Act: -0.1700
Data Index: 916881 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.3765. Min Act: -0.1700
Data Index: 1077628 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.4077. Min Act: -0.1700
Data Index: 5308991 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.4077. Min Act: -0.1700
Data Index: 5935738 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.3452. Min Act: -0.1700
Data Index: 8585833 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.3140. Min Act: -0.1700
Data Index: 7039105 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.3140. Min Act: -0.1700
Data Index: 390696 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.2827. Min Act: -0.1700
Data Index: 1722933 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.2827. Min Act: -0.1700
Data Index: 7945622 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.2827. Min Act: -0.1700
Data Index: 6521138 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.2515. Min Act: -0.1700
Data Index: 7718704 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.2515. Min Act: -0.1700
Data Index: 4826530 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8452. Min Range: -6.8452
Max Act: 6.2515. Min Act: -0.1700
Data Index: 156526 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19