Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.7013. Min Act: -0.1700
Data Index: 622921 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.7013. Min Act: -0.1695
Data Index: 7555533 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.6075. Min Act: -0.1700
Data Index: 8799824 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5763. Min Act: -0.1700
Data Index: 5013007 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.6075. Min Act: -0.1700
Data Index: 3821660 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.6075. Min Act: -0.1700
Data Index: 6415941 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5763. Min Act: -0.1700
Data Index: 5143171 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5450. Min Act: -0.1700
Data Index: 835895 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5450. Min Act: -0.1700
Data Index: 5485037 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5450. Min Act: -0.1700
Data Index: 1765162 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5450. Min Act: -0.1700
Data Index: 3328859 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5450. Min Act: -0.1700
Data Index: 6999990 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5138. Min Act: -0.1700
Data Index: 8750066 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5138. Min Act: -0.1700
Data Index: 3113564 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5138. Min Act: -0.1700
Data Index: 4557818 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.5138. Min Act: -0.1700
Data Index: 5214238 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.4825. Min Act: -0.1700
Data Index: 3557180 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.4825. Min Act: -0.1700
Data Index: 8013563 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.4825. Min Act: -0.1700
Data Index: 4384810 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7013. Min Range: -5.7013
Max Act: 5.4825. Min Act: -0.1700
Data Index: 5029396 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19