Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4828 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5014. Min Range: -10.5014
Max Act: 10.5014. Min Act: -0.1700
Data Index: 3538515 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5014. Min Range: -10.5014
Max Act: 10.2514. Min Act: -0.1700
Data Index: 2652130 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5014. Min Range: -10.5014
Max Act: 10.1264. Min Act: -0.1700
Data Index: 2652134 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5014. Min Range: -10.5014
Max Act: 10.0014. Min Act: -0.1700
Data Index: 7677325 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.9389. Min Act: -0.1700
Data Index: 4470254 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.8764. Min Act: -0.1700
Data Index: 6426647 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.8764. Min Act: -0.1700
Data Index: 1667929 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.8139. Min Act: -0.1700
Data Index: 1475463 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.8139. Min Act: -0.1700
Data Index: 5582216 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.8139. Min Act: -0.1700
Data Index: 4975537 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.7514. Min Act: -0.1700
Data Index: 593891 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.7514. Min Act: -0.1700
Data Index: 4775345 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.7514. Min Act: -0.1700
Data Index: 8139373 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.7514. Min Act: -0.1700
Data Index: 5758038 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.7514. Min Act: -0.1700
Data Index: 3915301 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.7514. Min Act: -0.1700
Data Index: 5112301 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.6889. Min Act: -0.1700
Data Index: 4391719 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.6889. Min Act: -0.1700
Data Index: 4849017 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.6889. Min Act: -0.1700
Data Index: 5551832 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5014. Min Range: -10.5014
Max Act: 9.6264. Min Act: -0.1700
Data Index: 6059865 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19