Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.7979. Min Act: -0.1700
Data Index: 3966716 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.7807. Min Act: -0.1700
Data Index: 2352015 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.7462. Min Act: -0.1700
Data Index: 1804589 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.7289. Min Act: -0.1699
Data Index: 4381144 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.7289. Min Act: -0.1700
Data Index: 176177 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6943. Min Act: -0.1700
Data Index: 7302962 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6769. Min Act: -0.1700
Data Index: 4355384 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6943. Min Act: -0.1698
Data Index: 7037394 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.7116. Min Act: -0.1700
Data Index: 6908801 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6943. Min Act: -0.1700
Data Index: 2496991 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6769. Min Act: -0.1700
Data Index: 2199616 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6595. Min Act: -0.1700
Data Index: 7884321 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6769. Min Act: -0.1700
Data Index: 7567429 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6769. Min Act: -0.1700
Data Index: 2631164 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6769. Min Act: -0.1698
Data Index: 4138430 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6769. Min Act: -0.1700
Data Index: 315367 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6595. Min Act: -0.1700
Data Index: 7211463 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6769. Min Act: -0.1700
Data Index: 5972926 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6595. Min Act: -0.1700
Data Index: 7147735 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7979. Min Range: -1.7979
Max Act: 1.6595. Min Act: -0.1700
Data Index: 3719382 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19