Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1932 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.3298. Min Act: -0.1700
Data Index: 5343362 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2673. Min Act: -0.1700
Data Index: 7487442 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2673. Min Act: -0.1700
Data Index: 4961490 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2673. Min Act: -0.1700
Data Index: 8760809 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2673. Min Act: -0.1700
Data Index: 8242586 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2360. Min Act: -0.1700
Data Index: 1811072 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2048. Min Act: -0.1700
Data Index: 3824682 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2048. Min Act: -0.1700
Data Index: 6254623 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2048. Min Act: -0.1700
Data Index: 6112452 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.1735. Min Act: -0.1700
Data Index: 716360 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2360. Min Act: -0.1700
Data Index: 1813265 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.1735. Min Act: -0.1700
Data Index: 3328723 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2048. Min Act: -0.1700
Data Index: 6606832 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.1735. Min Act: -0.1700
Data Index: 8510804 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.2048. Min Act: -0.1700
Data Index: 6744284 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.1423. Min Act: -0.1700
Data Index: 4451498 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.1423. Min Act: -0.1700
Data Index: 4492109 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.1735. Min Act: -0.1700
Data Index: 7470527 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.1423. Min Act: -0.1700
Data Index: 6778110 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3298. Min Range: -5.3298
Max Act: 5.1423. Min Act: -0.1700
Data Index: 4551304 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19