Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4245. Min Range: -4.4245
Max Act: 4.4245. Min Act: -0.1700
Data Index: 525306 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4245. Min Range: -4.4245
Max Act: 4.1745. Min Act: -0.1700
Data Index: 6567842 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4245. Min Range: -4.4245
Max Act: 4.0807. Min Act: -0.1700
Data Index: 7978141 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.9870. Min Act: -0.1700
Data Index: 3338369 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4245. Min Range: -4.4245
Max Act: 4.0495. Min Act: -0.1700
Data Index: 8537552 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.9870. Min Act: -0.1700
Data Index: 54594 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.9870. Min Act: -0.1700
Data Index: 3432038 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.9244. Min Act: -0.1700
Data Index: 1285425 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.9244. Min Act: -0.1700
Data Index: 1825367 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.8932. Min Act: -0.1700
Data Index: 8360706 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.8932. Min Act: -0.1700
Data Index: 6758426 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.8932. Min Act: -0.1700
Data Index: 8169625 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.9244. Min Act: -0.1700
Data Index: 8486832 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.8932. Min Act: -0.1700
Data Index: 2310355 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.8619. Min Act: -0.1700
Data Index: 1676218 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.8932. Min Act: -0.1700
Data Index: 2401925 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.8619. Min Act: -0.1700
Data Index: 412680 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.8619. Min Act: -0.1700
Data Index: 295715 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.8619. Min Act: -0.1700
Data Index: 1049829 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4245. Min Range: -4.4245
Max Act: 3.8619. Min Act: -0.1700
Data Index: 3454952 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19