Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 765 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0815. Min Act: -0.1659
Data Index: 1501473 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0640. Min Act: -0.1699
Data Index: 4358764 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0815. Min Act: -0.1680
Data Index: 4733059 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0815. Min Act: -0.1607
Data Index: 3002281 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0640. Min Act: -0.1549
Data Index: 26317 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0553. Min Act: -0.1615
Data Index: 3294378 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0553. Min Act: -0.1599
Data Index: 8232019 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0466. Min Act: -0.1694
Data Index: 4189073 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0466. Min Act: -0.1639
Data Index: 5416300 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0466. Min Act: -0.1491
Data Index: 2038446 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0379. Min Act: -0.1674
Data Index: 8142902 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0379. Min Act: -0.1491
Data Index: 4258181 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0379. Min Act: -0.1699
Data Index: 8726874 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0379. Min Act: -0.1549
Data Index: 5919037 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0379. Min Act: -0.1678
Data Index: 968880 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0466. Min Act: -0.1615
Data Index: 7710977 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0379. Min Act: -0.1400
Data Index: 4584004 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0379. Min Act: -0.1685
Data Index: 7275697 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0292. Min Act: -0.1358
Data Index: 715873 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0292. Min Act: -0.1615
Data Index: 4341253 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19