Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 167 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.7348. Min Act: -0.1700
Data Index: 2219494 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.6410. Min Act: -0.1700
Data Index: 7758825 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5785. Min Act: -0.1700
Data Index: 3163241 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4848. Min Act: -0.1700
Data Index: 8767542 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4848. Min Act: -0.1700
Data Index: 5445371 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4535. Min Act: -0.1700
Data Index: 7806191 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3910. Min Act: -0.1700
Data Index: 2948713 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3910. Min Act: -0.1700
Data Index: 8644801 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4223. Min Act: -0.1700
Data Index: 1617459 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4223. Min Act: -0.1700
Data Index: 6722123 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3285. Min Act: -0.1700
Data Index: 504866 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3598. Min Act: -0.1700
Data Index: 2760505 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3598. Min Act: -0.1700
Data Index: 5608162 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3598. Min Act: -0.1700
Data Index: 7195103 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3598. Min Act: -0.1700
Data Index: 7220212 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3285. Min Act: -0.1700
Data Index: 7247749 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2973. Min Act: -0.1700
Data Index: 8173048 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3285. Min Act: -0.1700
Data Index: 4987574 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2973. Min Act: -0.1700
Data Index: 896570 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3285. Min Act: -0.1700
Data Index: 6981915 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19