Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.4164. Min Act: -0.1700
Data Index: 535116 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.4164. Min Act: -0.1700
Data Index: 5648424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.4164. Min Act: -0.1700
Data Index: 4922207 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.4164. Min Act: -0.1700
Data Index: 1364026 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3852. Min Act: -0.1700
Data Index: 5568656 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3852. Min Act: -0.1700
Data Index: 7665634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3852. Min Act: -0.1700
Data Index: 4149793 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3852. Min Act: -0.1700
Data Index: 6890697 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 5511224 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 2507975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 8606103 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 8546267 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 7841692 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 5387500 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 4206377 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 55886 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 6254352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 5711606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 3396950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4164. Min Range: -4.4164
Max Act: 4.3539. Min Act: -0.1700
Data Index: 2662818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19