Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6165 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1017. Min Range: -6.1017
Max Act: 6.1017. Min Act: -0.1700
Data Index: 177708 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.9767. Min Act: -0.1700
Data Index: 4600512 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.9142. Min Act: -0.1700
Data Index: 5092079 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.8830. Min Act: -0.1700
Data Index: 8506366 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.8517. Min Act: -0.1700
Data Index: 5031555 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.8517. Min Act: -0.1700
Data Index: 2629018 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7892. Min Act: -0.1700
Data Index: 580419 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7580. Min Act: -0.1700
Data Index: 6614161 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7267. Min Act: -0.1700
Data Index: 4793686 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6955. Min Act: -0.1700
Data Index: 8018524 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6955. Min Act: -0.1700
Data Index: 630694 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6955. Min Act: -0.1700
Data Index: 1086235 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6642. Min Act: -0.1700
Data Index: 1983809 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6330. Min Act: -0.1700
Data Index: 4606765 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6330. Min Act: -0.1700
Data Index: 5705443 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6017. Min Act: -0.1700
Data Index: 1165692 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6017. Min Act: -0.1700
Data Index: 7289053 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6017. Min Act: -0.1700
Data Index: 2979683 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6017. Min Act: -0.1700
Data Index: 5527716 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6017. Min Act: -0.1700
Data Index: 1522367 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19