Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 537 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.9378. Min Act: -0.1700
Data Index: 7112740 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.9061. Min Act: -0.1700
Data Index: 7799451 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.9378. Min Act: -0.1700
Data Index: 6606561 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8903. Min Act: -0.1700
Data Index: 3806156 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8744. Min Act: -0.1700
Data Index: 8776313 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8903. Min Act: -0.1700
Data Index: 6982586 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8744. Min Act: -0.1700
Data Index: 68876 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8744. Min Act: -0.1700
Data Index: 5771039 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8585. Min Act: -0.1700
Data Index: 7394460 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8267. Min Act: -0.1700
Data Index: 4935007 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8744. Min Act: -0.1700
Data Index: 8320124 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8585. Min Act: -0.1700
Data Index: 8716673 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8426. Min Act: -0.1700
Data Index: 1734763 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8585. Min Act: -0.1700
Data Index: 4797172 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8585. Min Act: -0.1700
Data Index: 5585004 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8585. Min Act: -0.1700
Data Index: 935015 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8108. Min Act: -0.1700
Data Index: 1870618 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8108. Min Act: -0.1700
Data Index: 7714419 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8108. Min Act: -0.1700
Data Index: 3109380 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9378. Min Range: -2.9378
Max Act: 2.8108. Min Act: -0.1700
Data Index: 3675445 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19