Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8512. Min Range: -8.8512
Max Act: 8.8512. Min Act: -0.1700
Data Index: 1050159 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8512. Min Range: -8.8512
Max Act: 8.4137. Min Act: -0.1700
Data Index: 353746 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8512. Min Range: -8.8512
Max Act: 8.2887. Min Act: -0.1700
Data Index: 2789039 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8512. Min Range: -8.8512
Max Act: 8.2887. Min Act: -0.1700
Data Index: 1728323 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8512. Min Range: -8.8512
Max Act: 8.2262. Min Act: -0.1700
Data Index: 57776 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8512. Min Range: -8.8512
Max Act: 8.1637. Min Act: -0.1700
Data Index: 5374753 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8512. Min Range: -8.8512
Max Act: 8.1637. Min Act: -0.1700
Data Index: 2206363 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8512. Min Range: -8.8512
Max Act: 8.0387. Min Act: -0.1700
Data Index: 5087067 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8512. Min Range: -8.8512
Max Act: 8.0387. Min Act: -0.1700
Data Index: 6903143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.9137. Min Act: -0.1700
Data Index: 6238394 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.9137. Min Act: -0.1700
Data Index: 5000568 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.8825. Min Act: -0.1700
Data Index: 1563511 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.8825. Min Act: -0.1700
Data Index: 849016 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.8825. Min Act: -0.1700
Data Index: 4749158 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.8512. Min Act: -0.1700
Data Index: 7230311 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.8512. Min Act: -0.1700
Data Index: 6902865 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.8512. Min Act: -0.1700
Data Index: 5813415 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.8200. Min Act: -0.1700
Data Index: 108250 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.8200. Min Act: -0.1700
Data Index: 7100134 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8512. Min Range: -8.8512
Max Act: 7.7887. Min Act: -0.1700
Data Index: 2393541 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19