Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1034 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.9077. Min Act: -0.1700
Data Index: 142875 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.8452. Min Act: -0.1700
Data Index: 383149 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.8764. Min Act: -0.1700
Data Index: 6920898 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.8452. Min Act: -0.1700
Data Index: 1924523 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.8452. Min Act: -0.1700
Data Index: 60707 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.8452. Min Act: -0.1700
Data Index: 4903531 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.8139. Min Act: -0.1700
Data Index: 8533721 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7827. Min Act: -0.1700
Data Index: 2063977 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7514. Min Act: -0.1700
Data Index: 6682779 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7514. Min Act: -0.1700
Data Index: 8765249 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7514. Min Act: -0.1700
Data Index: 1359775 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7514. Min Act: -0.1700
Data Index: 8737676 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7514. Min Act: -0.1700
Data Index: 4211963 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.6889. Min Act: -0.1700
Data Index: 8403333 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7202. Min Act: -0.1700
Data Index: 3149704 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7202. Min Act: -0.1700
Data Index: 6187655 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7202. Min Act: -0.1700
Data Index: 2468422 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7202. Min Act: -0.1700
Data Index: 821447 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7202. Min Act: -0.1700
Data Index: 307025 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9077. Min Range: -5.9077
Max Act: 5.7514. Min Act: -0.1700
Data Index: 6739373 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19