Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0032. Min Range: -7.0032
Max Act: 7.0032. Min Act: -0.1700
Data Index: 4974219 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.9407. Min Act: -0.1700
Data Index: 3270230 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.7845. Min Act: -0.1700
Data Index: 7492676 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.6595. Min Act: -0.1700
Data Index: 1022878 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.6907. Min Act: -0.1700
Data Index: 7463735 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.6907. Min Act: -0.1700
Data Index: 2429127 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.6595. Min Act: -0.1700
Data Index: 1825531 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.6282. Min Act: -0.1700
Data Index: 3326561 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.6282. Min Act: -0.1700
Data Index: 5262759 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.5970. Min Act: -0.1700
Data Index: 6296935 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.6282. Min Act: -0.1700
Data Index: 3062503 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.5970. Min Act: -0.1700
Data Index: 1071376 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.5657. Min Act: -0.1700
Data Index: 1799269 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.5657. Min Act: -0.1700
Data Index: 2912601 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.5657. Min Act: -0.1700
Data Index: 7242065 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.5657. Min Act: -0.1700
Data Index: 6721996 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.5657. Min Act: -0.1700
Data Index: 4441024 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.5657. Min Act: -0.1700
Data Index: 6353809 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.5032. Min Act: -0.1700
Data Index: 7228042 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0032. Min Range: -7.0032
Max Act: 6.5345. Min Act: -0.1700
Data Index: 1798092 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19