Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.9787. Min Act: -0.1700
Data Index: 2417092 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.9162. Min Act: -0.1700
Data Index: 52260 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.8537. Min Act: -0.1700
Data Index: 2194740 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.7912. Min Act: -0.1700
Data Index: 862725 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.7287. Min Act: -0.1700
Data Index: 3456609 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6975. Min Act: -0.1700
Data Index: 1095891 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.7287. Min Act: -0.1700
Data Index: 6903678 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6975. Min Act: -0.1700
Data Index: 7471151 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6975. Min Act: -0.1700
Data Index: 7227125 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6975. Min Act: -0.1700
Data Index: 5641545 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6662. Min Act: -0.1700
Data Index: 6958952 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6662. Min Act: -0.1700
Data Index: 2453170 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6662. Min Act: -0.1700
Data Index: 8501734 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6662. Min Act: -0.1700
Data Index: 2255634 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6350. Min Act: -0.1700
Data Index: 4837128 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6350. Min Act: -0.1700
Data Index: 2293149 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6350. Min Act: -0.1700
Data Index: 4530279 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6350. Min Act: -0.1700
Data Index: 3537457 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6037. Min Act: -0.1700
Data Index: 6385570 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9787. Min Range: -6.9787
Max Act: 6.6037. Min Act: -0.1700
Data Index: 7130484 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19