Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4988 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.3026. Min Act: -0.1700
Data Index: 4687034 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.2714. Min Act: -0.1700
Data Index: 37033 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.1776. Min Act: -0.1700
Data Index: 660122 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.2089. Min Act: -0.1700
Data Index: 3557496 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.1464. Min Act: -0.1700
Data Index: 8521487 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.1464. Min Act: -0.1700
Data Index: 4957204 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.0839. Min Act: -0.1700
Data Index: 3834407 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.0839. Min Act: -0.1700
Data Index: 2132664 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.0839. Min Act: -0.1700
Data Index: 2106119 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.0526. Min Act: -0.1700
Data Index: 8492821 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.0214. Min Act: -0.1700
Data Index: 2196704 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.0214. Min Act: -0.1700
Data Index: 6557326 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.0214. Min Act: -0.1700
Data Index: 3380951 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.0214. Min Act: -0.1700
Data Index: 2950231 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.0214. Min Act: -0.1700
Data Index: 1287636 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3026. Min Range: -5.3026
Max Act: 5.0214. Min Act: -0.1700
Data Index: 8062822 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3026. Min Range: -5.3026
Max Act: 4.9901. Min Act: -0.1700
Data Index: 5964026 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3026. Min Range: -5.3026
Max Act: 4.9901. Min Act: -0.1700
Data Index: 7198137 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3026. Min Range: -5.3026
Max Act: 4.9901. Min Act: -0.1700
Data Index: 7525750 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3026. Min Range: -5.3026
Max Act: 4.9901. Min Act: -0.1700
Data Index: 3517810 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19