Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5353 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.9393. Min Act: -0.1700
Data Index: 4279097 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.7831. Min Act: -0.1700
Data Index: 4449382 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.6893. Min Act: -0.1700
Data Index: 8173251 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.7206. Min Act: -0.1700
Data Index: 1042544 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.6581. Min Act: -0.1700
Data Index: 619583 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.6268. Min Act: -0.1700
Data Index: 5608143 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.6268. Min Act: -0.1700
Data Index: 376786 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.5331. Min Act: -0.1700
Data Index: 473766 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.5643. Min Act: -0.1700
Data Index: 5374679 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.5956. Min Act: -0.1700
Data Index: 2887480 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.5331. Min Act: -0.1700
Data Index: 5508185 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.5331. Min Act: -0.1700
Data Index: 7992412 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.4706. Min Act: -0.1700
Data Index: 2251216 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.4393. Min Act: -0.1700
Data Index: 5490366 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.4081. Min Act: -0.1700
Data Index: 1742550 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.3768. Min Act: -0.1700
Data Index: 7021057 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.3768. Min Act: -0.1700
Data Index: 2131228 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.3456. Min Act: -0.1700
Data Index: 5435776 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.3456. Min Act: -0.1700
Data Index: 4143986 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9393. Min Range: -7.9393
Max Act: 7.3143. Min Act: -0.1700
Data Index: 4605775 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19