Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.7979. Min Act: -0.1700
Data Index: 7804666 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.7666. Min Act: -0.1700
Data Index: 3043624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.7040. Min Act: -0.1700
Data Index: 4337217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.6727. Min Act: -0.1700
Data Index: 3470398 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.6415. Min Act: -0.1700
Data Index: 6574925 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.6415. Min Act: -0.1700
Data Index: 6014619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.6102. Min Act: -0.1700
Data Index: 2030571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5788. Min Act: -0.1700
Data Index: 7637326 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.6102. Min Act: -0.1700
Data Index: 8335518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.6102. Min Act: -0.1700
Data Index: 5412437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5788. Min Act: -0.1700
Data Index: 184766 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5788. Min Act: -0.1700
Data Index: 5933943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5788. Min Act: -0.1700
Data Index: 5565555 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5788. Min Act: -0.1700
Data Index: 1371764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5788. Min Act: -0.1700
Data Index: 1311169 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5788. Min Act: -0.1700
Data Index: 2481312 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5788. Min Act: -0.1700
Data Index: 5525378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5788. Min Act: -0.1700
Data Index: 8817664 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5788. Min Act: -0.1700
Data Index: 4823019 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7979. Min Range: -3.7979
Max Act: 3.5475. Min Act: -0.1700
Data Index: 2668712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19