Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.9010. Min Act: -0.1700
Data Index: 4201259 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.8697. Min Act: -0.1700
Data Index: 893333 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.8385. Min Act: -0.1700
Data Index: 5962873 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.8385. Min Act: -0.1700
Data Index: 1590625 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.8072. Min Act: -0.1700
Data Index: 1506332 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.8072. Min Act: -0.1700
Data Index: 4034612 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.8072. Min Act: -0.1700
Data Index: 2413389 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.7760. Min Act: -0.1700
Data Index: 1787693 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.7760. Min Act: -0.1700
Data Index: 4400770 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.7760. Min Act: -0.1700
Data Index: 7977741 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.7135. Min Act: -0.1700
Data Index: 3018662 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.7447. Min Act: -0.1700
Data Index: 117327 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.7135. Min Act: -0.1700
Data Index: 1506334 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.7135. Min Act: -0.1700
Data Index: 146919 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.7135. Min Act: -0.1700
Data Index: 5498727 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.6822. Min Act: -0.1700
Data Index: 6604619 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.7447. Min Act: -0.1700
Data Index: 4311827 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.6510. Min Act: -0.1700
Data Index: 3051440 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.7447. Min Act: -0.1700
Data Index: 3682568 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.6822. Min Act: -0.1700
Data Index: 2538496 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19