Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.7062. Min Act: -0.1700
Data Index: 1123700 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.6749. Min Act: -0.1698
Data Index: 7676971 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.6749. Min Act: -0.1700
Data Index: 7676973 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.6749. Min Act: -0.1700
Data Index: 3248105 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.6437. Min Act: -0.1700
Data Index: 7676972 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.6437. Min Act: -0.1700
Data Index: 347651 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.6124. Min Act: -0.1700
Data Index: 3169342 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.6124. Min Act: -0.1700
Data Index: 1704797 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5812. Min Act: -0.1700
Data Index: 2117809 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5812. Min Act: -0.1700
Data Index: 7906268 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5812. Min Act: -0.1700
Data Index: 7767130 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5499. Min Act: -0.1700
Data Index: 8121934 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5499. Min Act: -0.1700
Data Index: 1535866 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5499. Min Act: -0.1698
Data Index: 8269817 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5499. Min Act: -0.1700
Data Index: 1359746 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5499. Min Act: -0.1700
Data Index: 4315850 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5187. Min Act: -0.1700
Data Index: 7104073 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5187. Min Act: -0.1700
Data Index: 7517941 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5187. Min Act: -0.1700
Data Index: 2683850 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7062. Min Range: -5.7062
Max Act: 5.5187. Min Act: -0.1700
Data Index: 2870163 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19