Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1994 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0188. Min Range: -5.0188
Max Act: 5.0188. Min Act: -0.1700
Data Index: 6616352 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.9563. Min Act: -0.1700
Data Index: 3813780 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.9563. Min Act: -0.1700
Data Index: 6616347 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.9563. Min Act: -0.1700
Data Index: 4739751 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.8938. Min Act: -0.1700
Data Index: 3813784 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.8001. Min Act: -0.1700
Data Index: 3918127 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.7688. Min Act: -0.1700
Data Index: 7672028 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.7063. Min Act: -0.1700
Data Index: 5964075 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.7376. Min Act: -0.1700
Data Index: 5236535 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.7376. Min Act: -0.1700
Data Index: 4539527 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.7063. Min Act: -0.1700
Data Index: 3929941 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.6751. Min Act: -0.1700
Data Index: 356275 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.6751. Min Act: -0.1700
Data Index: 1038916 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.6438. Min Act: -0.1700
Data Index: 4152535 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.6438. Min Act: -0.1700
Data Index: 8098622 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.6438. Min Act: -0.1700
Data Index: 4937837 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.6438. Min Act: -0.1700
Data Index: 1857060 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.6438. Min Act: -0.1700
Data Index: 2923787 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.6126. Min Act: -0.1700
Data Index: 2973403 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0188. Min Range: -5.0188
Max Act: 4.5813. Min Act: -0.1700
Data Index: 2305443 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19