Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4372 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0313. Min Range: -8.0313
Max Act: 8.0313. Min Act: -0.1700
Data Index: 4600436 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.9063. Min Act: -0.1700
Data Index: 4479649 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.7188. Min Act: -0.1700
Data Index: 5029345 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.6563. Min Act: -0.1700
Data Index: 4616710 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.5938. Min Act: -0.1700
Data Index: 5379344 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.5938. Min Act: -0.1700
Data Index: 2465553 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.5938. Min Act: -0.1700
Data Index: 1799637 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.5625. Min Act: -0.1700
Data Index: 650448 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.5313. Min Act: -0.1700
Data Index: 7250310 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.5938. Min Act: -0.1700
Data Index: 8646132 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.5625. Min Act: -0.1700
Data Index: 6148518 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.5313. Min Act: -0.1700
Data Index: 1009611 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.5313. Min Act: -0.1700
Data Index: 6922802 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.5313. Min Act: -0.1700
Data Index: 1719184 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.4688. Min Act: -0.1700
Data Index: 7106257 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.4688. Min Act: -0.1700
Data Index: 632952 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.4063. Min Act: -0.1700
Data Index: 8496640 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.4375. Min Act: -0.1700
Data Index: 476849 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.4375. Min Act: -0.1700
Data Index: 1190060 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0313. Min Range: -8.0313
Max Act: 7.4063. Min Act: -0.1700
Data Index: 8134938 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19