Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 269 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.8418. Min Act: -0.1700
Data Index: 775710 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.8106. Min Act: -0.1700
Data Index: 479831 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.8106. Min Act: -0.1699
Data Index: 294478 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7793. Min Act: -0.1700
Data Index: 5810004 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7793. Min Act: -0.1700
Data Index: 3331210 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 5704117 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 196200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1698
Data Index: 7928175 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 6947853 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 6179992 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 594634 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 3219180 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 1138250 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 4835857 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 3039192 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 45869 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 5491517 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 5373771 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 2867841 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8418. Min Range: -4.8418
Max Act: 4.7481. Min Act: -0.1700
Data Index: 2503957 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19