Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4022 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.9449. Min Act: -0.1700
Data Index: 7552406 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.9449. Min Act: -0.1700
Data Index: 7177652 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.8339. Min Act: -0.1700
Data Index: 600267 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7824. Min Act: -0.1700
Data Index: 8148420 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7824. Min Act: -0.1700
Data Index: 8034850 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7737. Min Act: -0.1700
Data Index: 1044997 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7737. Min Act: -0.1700
Data Index: 5988409 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7565. Min Act: -0.1700
Data Index: 7247253 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7565. Min Act: -0.1700
Data Index: 333857 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7651. Min Act: -0.1700
Data Index: 6363223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7565. Min Act: -0.1700
Data Index: 2128027 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7306. Min Act: -0.1700
Data Index: 7732087 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7478. Min Act: -0.1700
Data Index: 4263655 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7306. Min Act: -0.1700
Data Index: 7415791 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7306. Min Act: -0.1700
Data Index: 8076777 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7219. Min Act: -0.1700
Data Index: 5465590 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7219. Min Act: -0.1700
Data Index: 7293071 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7219. Min Act: -0.1700
Data Index: 4359784 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7219. Min Act: -0.1700
Data Index: 1486511 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9449. Min Range: -1.9449
Max Act: 1.7306. Min Act: -0.1700
Data Index: 1959900 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19