Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5530 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0719. Min Range: -7.0719
Max Act: 7.0719. Min Act: -0.1700
Data Index: 4235570 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0719. Min Range: -7.0719
Max Act: 7.0094. Min Act: -0.1700
Data Index: 3172402 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0719. Min Range: -7.0719
Max Act: 7.0094. Min Act: -0.1700
Data Index: 8802032 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.9469. Min Act: -0.1700
Data Index: 436279 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.8844. Min Act: -0.1700
Data Index: 5013027 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.8219. Min Act: -0.1700
Data Index: 4821486 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.7906. Min Act: -0.1700
Data Index: 1886066 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.7594. Min Act: -0.1700
Data Index: 8098368 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.7906. Min Act: -0.1700
Data Index: 2868656 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.7906. Min Act: -0.1700
Data Index: 1141896 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.7906. Min Act: -0.1700
Data Index: 5652795 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.7594. Min Act: -0.1700
Data Index: 6546001 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.7281. Min Act: -0.1700
Data Index: 7363634 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.7281. Min Act: -0.1700
Data Index: 3998552 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.6656. Min Act: -0.1700
Data Index: 6936214 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.6969. Min Act: -0.1700
Data Index: 5166196 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.6969. Min Act: -0.1700
Data Index: 3343719 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.6656. Min Act: -0.1700
Data Index: 6095016 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.6344. Min Act: -0.1700
Data Index: 790966 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0719. Min Range: -7.0719
Max Act: 6.6344. Min Act: -0.1700
Data Index: 7367791 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19