Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3865 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0811. Min Range: -5.0811
Max Act: 5.0811. Min Act: -0.1700
Data Index: 6883102 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.9874. Min Act: -0.1700
Data Index: 4115697 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.9561. Min Act: -0.1700
Data Index: 5720288 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.9561. Min Act: -0.1700
Data Index: 6883084 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.8624. Min Act: -0.1700
Data Index: 2778525 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.8311. Min Act: -0.1700
Data Index: 980141 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.7374. Min Act: -0.1700
Data Index: 1087816 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.7374. Min Act: -0.1700
Data Index: 6307800 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.7686. Min Act: -0.1700
Data Index: 4488688 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.7374. Min Act: -0.1700
Data Index: 6883070 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.7374. Min Act: -0.1700
Data Index: 4458711 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.7061. Min Act: -0.1700
Data Index: 6066106 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.7374. Min Act: -0.1700
Data Index: 980139 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.7061. Min Act: -0.1700
Data Index: 8225112 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.7061. Min Act: -0.1700
Data Index: 1485670 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.7061. Min Act: -0.1700
Data Index: 6033643 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.6749. Min Act: -0.1700
Data Index: 1485669 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.6436. Min Act: -0.1700
Data Index: 7262266 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.6436. Min Act: -0.1700
Data Index: 7262264 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0811. Min Range: -5.0811
Max Act: 4.6124. Min Act: -0.1700
Data Index: 642866 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19