Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1803. Min Range: -7.1803
Max Act: 7.1803. Min Act: -0.1700
Data Index: 3498140 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1803. Min Range: -7.1803
Max Act: 7.1178. Min Act: -0.1700
Data Index: 2070625 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1803. Min Range: -7.1803
Max Act: 7.0866. Min Act: -0.1700
Data Index: 5175657 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.9616. Min Act: -0.1700
Data Index: 3209979 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.9928. Min Act: -0.1700
Data Index: 7464801 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.9928. Min Act: -0.1700
Data Index: 4556550 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.9616. Min Act: -0.1700
Data Index: 334477 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.9616. Min Act: -0.1700
Data Index: 8410891 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.9303. Min Act: -0.1700
Data Index: 1054576 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.9303. Min Act: -0.1700
Data Index: 1617461 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.8991. Min Act: -0.1700
Data Index: 7313872 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.8678. Min Act: -0.1700
Data Index: 1008501 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.8678. Min Act: -0.1700
Data Index: 5875666 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.9303. Min Act: -0.1700
Data Index: 5671316 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.8678. Min Act: -0.1700
Data Index: 1791920 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.8678. Min Act: -0.1700
Data Index: 2131042 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.8678. Min Act: -0.1700
Data Index: 6499162 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.8366. Min Act: -0.1700
Data Index: 6406409 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.8053. Min Act: -0.1700
Data Index: 2971155 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1803. Min Range: -7.1803
Max Act: 6.8366. Min Act: -0.1700
Data Index: 4709711 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19