Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.6116. Min Act: -0.1699
Data Index: 3748909 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.6029. Min Act: -0.1700
Data Index: 31152 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5766. Min Act: -0.1700
Data Index: 8121301 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5679. Min Act: -0.1700
Data Index: 3611370 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5766. Min Act: -0.1700
Data Index: 2571696 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5766. Min Act: -0.1700
Data Index: 3386117 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5679. Min Act: -0.1700
Data Index: 2819476 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5591. Min Act: -0.1699
Data Index: 5276350 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5591. Min Act: -0.1700
Data Index: 2008290 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5504. Min Act: -0.1700
Data Index: 7276437 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5591. Min Act: -0.1700
Data Index: 4923077 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5416. Min Act: -0.1700
Data Index: 2334778 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5504. Min Act: -0.1696
Data Index: 2952611 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5504. Min Act: -0.1692
Data Index: 8576594 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5504. Min Act: -0.1700
Data Index: 5719115 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5504. Min Act: -0.1700
Data Index: 5719116 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5329. Min Act: -0.1700
Data Index: 4381364 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5329. Min Act: -0.1700
Data Index: 7276435 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5504. Min Act: -0.1700
Data Index: 4514073 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6116. Min Range: -1.6116
Max Act: 1.5416. Min Act: -0.1698
Data Index: 6717085 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19