Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7828. Min Range: -7.7828
Max Act: 7.7828. Min Act: -0.1700
Data Index: 1364424 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7828. Min Range: -7.7828
Max Act: 7.4703. Min Act: -0.1700
Data Index: 8182525 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7828. Min Range: -7.7828
Max Act: 7.1891. Min Act: -0.1700
Data Index: 6175953 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7828. Min Range: -7.7828
Max Act: 7.1578. Min Act: -0.1700
Data Index: 1292506 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7828. Min Range: -7.7828
Max Act: 7.0328. Min Act: -0.1700
Data Index: 6792148 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7828. Min Range: -7.7828
Max Act: 7.0016. Min Act: -0.1700
Data Index: 1839183 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7828. Min Range: -7.7828
Max Act: 7.0016. Min Act: -0.1700
Data Index: 8668859 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.9703. Min Act: -0.1700
Data Index: 5548725 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7828. Min Range: -7.7828
Max Act: 7.0016. Min Act: -0.1700
Data Index: 4923243 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.9078. Min Act: -0.1700
Data Index: 7094323 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.8766. Min Act: -0.1700
Data Index: 6755444 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.8766. Min Act: -0.1700
Data Index: 455748 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.8141. Min Act: -0.1700
Data Index: 2784485 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.8141. Min Act: -0.1700
Data Index: 5886634 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.7516. Min Act: -0.1700
Data Index: 6590688 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.7203. Min Act: -0.1700
Data Index: 6340948 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.7203. Min Act: -0.1700
Data Index: 1796736 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.6891. Min Act: -0.1700
Data Index: 4678139 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.6891. Min Act: -0.1700
Data Index: 2229693 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7828. Min Range: -7.7828
Max Act: 6.6891. Min Act: -0.1700
Data Index: 5930940 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19