Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 859 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0180. Min Range: -6.0180
Max Act: 6.0180. Min Act: -0.1700
Data Index: 8063262 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.8617. Min Act: -0.1700
Data Index: 4935683 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.8617. Min Act: -0.1700
Data Index: 3606526 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.7992. Min Act: -0.1700
Data Index: 6516795 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.7992. Min Act: -0.1700
Data Index: 2635052 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.7367. Min Act: -0.1700
Data Index: 3358250 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.7367. Min Act: -0.1700
Data Index: 5108697 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.7055. Min Act: -0.1700
Data Index: 3336696 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.7055. Min Act: -0.1700
Data Index: 1698458 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.7055. Min Act: -0.1700
Data Index: 2508111 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.7055. Min Act: -0.1700
Data Index: 1309167 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.6742. Min Act: -0.1700
Data Index: 978064 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.6117. Min Act: -0.1700
Data Index: 83539 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.5805. Min Act: -0.1700
Data Index: 616792 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.6117. Min Act: -0.1700
Data Index: 4254634 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.5805. Min Act: -0.1700
Data Index: 6793718 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.5805. Min Act: -0.1700
Data Index: 6672856 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.5805. Min Act: -0.1700
Data Index: 3030327 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.5805. Min Act: -0.1700
Data Index: 1064685 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0180. Min Range: -6.0180
Max Act: 5.6117. Min Act: -0.1700
Data Index: 313029 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19