Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1630 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2139. Min Range: -9.2139
Max Act: 9.2139. Min Act: -0.1700
Data Index: 944696 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.9639. Min Act: -0.1700
Data Index: 4449637 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.9014. Min Act: -0.1700
Data Index: 6078973 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.9014. Min Act: -0.1700
Data Index: 6186300 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.8389. Min Act: -0.1700
Data Index: 3992887 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.7139. Min Act: -0.1700
Data Index: 6780532 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.7764. Min Act: -0.1700
Data Index: 8025671 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.7139. Min Act: -0.1700
Data Index: 8236170 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.7139. Min Act: -0.1700
Data Index: 8495535 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.6514. Min Act: -0.1700
Data Index: 2877461 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.5889. Min Act: -0.1700
Data Index: 2597159 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.5889. Min Act: -0.1700
Data Index: 3885367 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.5889. Min Act: -0.1700
Data Index: 881359 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.5889. Min Act: -0.1700
Data Index: 260397 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.5889. Min Act: -0.1700
Data Index: 6718312 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.5889. Min Act: -0.1700
Data Index: 4116197 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.6514. Min Act: -0.1700
Data Index: 6198348 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.5889. Min Act: -0.1700
Data Index: 6181121 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.5889. Min Act: -0.1700
Data Index: 7443238 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2139. Min Range: -9.2139
Max Act: 8.5889. Min Act: -0.1700
Data Index: 4120880 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19