Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 909 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.5252. Min Act: -0.1700
Data Index: 5458318 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.1502. Min Act: -0.1700
Data Index: 8065335 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.1190. Min Act: -0.1700
Data Index: 1650585 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.1815. Min Act: -0.1700
Data Index: 8424628 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.1815. Min Act: -0.1700
Data Index: 3924096 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.1502. Min Act: -0.1700
Data Index: 3788588 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.0565. Min Act: -0.1700
Data Index: 3542417 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.9940. Min Act: -0.1700
Data Index: 1886028 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.0252. Min Act: -0.1700
Data Index: 4159504 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.9940. Min Act: -0.1700
Data Index: 8097513 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.0252. Min Act: -0.1700
Data Index: 3167287 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.9002. Min Act: -0.1700
Data Index: 1450496 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.9627. Min Act: -0.1700
Data Index: 4533977 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.9627. Min Act: -0.1700
Data Index: 3707685 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.9002. Min Act: -0.1700
Data Index: 6963388 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.8690. Min Act: -0.1700
Data Index: 3607865 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.9002. Min Act: -0.1700
Data Index: 5342664 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.8690. Min Act: -0.1700
Data Index: 6256300 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.8690. Min Act: -0.1700
Data Index: 1374666 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5252. Min Range: -6.5252
Max Act: 5.8065. Min Act: -0.1700
Data Index: 5250668 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19