Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4328 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5900. Min Range: -9.5900
Max Act: 9.5900. Min Act: -0.1700
Data Index: 4167750 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5900. Min Range: -9.5900
Max Act: 9.4650. Min Act: -0.1700
Data Index: 6120442 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5900. Min Range: -9.5900
Max Act: 9.2775. Min Act: -0.1700
Data Index: 5397481 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5900. Min Range: -9.5900
Max Act: 9.2150. Min Act: -0.1700
Data Index: 8526544 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5900. Min Range: -9.5900
Max Act: 9.0900. Min Act: -0.1700
Data Index: 1014881 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.9025. Min Act: -0.1700
Data Index: 7061074 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.8400. Min Act: -0.1700
Data Index: 3914863 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.8400. Min Act: -0.1700
Data Index: 1684963 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.8400. Min Act: -0.1700
Data Index: 1605724 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.8400. Min Act: -0.1700
Data Index: 6513175 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.7775. Min Act: -0.1700
Data Index: 5211424 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.7775. Min Act: -0.1700
Data Index: 5201108 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.7775. Min Act: -0.1700
Data Index: 1015123 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.7150. Min Act: -0.1700
Data Index: 3039366 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.6525. Min Act: -0.1700
Data Index: 6028865 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.6525. Min Act: -0.1700
Data Index: 1392334 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.6525. Min Act: -0.1700
Data Index: 1489886 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.6525. Min Act: -0.1700
Data Index: 3651720 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.5900. Min Act: -0.1700
Data Index: 7629992 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5900. Min Range: -9.5900
Max Act: 8.5900. Min Act: -0.1700
Data Index: 2855081 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19