Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1481 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3185. Min Range: -7.3185
Max Act: 7.3185. Min Act: -0.1700
Data Index: 3533001 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3185. Min Range: -7.3185
Max Act: 7.2560. Min Act: -0.1700
Data Index: 5505754 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3185. Min Range: -7.3185
Max Act: 7.2560. Min Act: -0.1700
Data Index: 4655428 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3185. Min Range: -7.3185
Max Act: 7.2560. Min Act: -0.1700
Data Index: 6677376 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3185. Min Range: -7.3185
Max Act: 7.2247. Min Act: -0.1700
Data Index: 6868439 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3185. Min Range: -7.3185
Max Act: 7.0685. Min Act: -0.1700
Data Index: 3693677 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3185. Min Range: -7.3185
Max Act: 7.0060. Min Act: -0.1700
Data Index: 3588669 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.9747. Min Act: -0.1700
Data Index: 6470931 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.9747. Min Act: -0.1700
Data Index: 8292321 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.9747. Min Act: -0.1700
Data Index: 5505842 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.9747. Min Act: -0.1700
Data Index: 6169718 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.8810. Min Act: -0.1700
Data Index: 7809087 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.8497. Min Act: -0.1700
Data Index: 4594302 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.9435. Min Act: -0.1700
Data Index: 4617203 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.8810. Min Act: -0.1700
Data Index: 7499017 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.8497. Min Act: -0.1700
Data Index: 481826 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.8497. Min Act: -0.1700
Data Index: 333927 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.8497. Min Act: -0.1700
Data Index: 7116539 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.7872. Min Act: -0.1700
Data Index: 1699640 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3185. Min Range: -7.3185
Max Act: 6.7560. Min Act: -0.1700
Data Index: 4850322 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19