Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 657 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.8865. Min Act: -0.1700
Data Index: 8458352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.7836. Min Act: -0.1700
Data Index: 4189209 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.7404. Min Act: -0.1699
Data Index: 1476300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.7145. Min Act: -0.1700
Data Index: 1957356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.7231. Min Act: -0.1698
Data Index: 8299033 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.7145. Min Act: -0.1700
Data Index: 4298370 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6971. Min Act: -0.1700
Data Index: 483914 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6885. Min Act: -0.1700
Data Index: 2269410 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6885. Min Act: -0.1700
Data Index: 6674035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6798. Min Act: -0.1700
Data Index: 8275400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6798. Min Act: -0.1698
Data Index: 816395 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6798. Min Act: -0.1700
Data Index: 1280490 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6711. Min Act: -0.1700
Data Index: 8040471 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6711. Min Act: -0.1700
Data Index: 4275765 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6537. Min Act: -0.1700
Data Index: 1661503 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6711. Min Act: -0.1699
Data Index: 395880 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6537. Min Act: -0.1700
Data Index: 1654664 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6624. Min Act: -0.1697
Data Index: 3622007 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6624. Min Act: -0.1689
Data Index: 1029332 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8865. Min Range: -1.8865
Max Act: 1.6450. Min Act: -0.1700
Data Index: 5798108 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19