Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0290. Min Range: -8.0290
Max Act: 8.0290. Min Act: -0.1700
Data Index: 2225371 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0290. Min Range: -8.0290
Max Act: 8.0290. Min Act: -0.1700
Data Index: 5041017 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.9353. Min Act: -0.1700
Data Index: 6188593 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.9665. Min Act: -0.1700
Data Index: 6188600 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.9665. Min Act: -0.1700
Data Index: 3427747 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.9353. Min Act: -0.1700
Data Index: 3186744 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.9040. Min Act: -0.1700
Data Index: 4811474 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.8415. Min Act: -0.1700
Data Index: 2085127 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.8415. Min Act: -0.1700
Data Index: 3186737 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.8103. Min Act: -0.1700
Data Index: 2844167 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.8103. Min Act: -0.1700
Data Index: 3186740 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.8103. Min Act: -0.1700
Data Index: 7692327 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.7165. Min Act: -0.1700
Data Index: 4811468 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.7790. Min Act: -0.1700
Data Index: 6670831 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.6853. Min Act: -0.1700
Data Index: 8115790 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.6540. Min Act: -0.1700
Data Index: 732845 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.6540. Min Act: -0.1700
Data Index: 7686676 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.6853. Min Act: -0.1700
Data Index: 1000241 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.6228. Min Act: -0.1700
Data Index: 6114699 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0290. Min Range: -8.0290
Max Act: 7.6540. Min Act: -0.1700
Data Index: 4183087 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19