Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0341. Min Range: -6.0341
Max Act: 6.0341. Min Act: -0.1700
Data Index: 7654993 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.9716. Min Act: -0.1700
Data Index: 5102729 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.9404. Min Act: -0.1700
Data Index: 8769176 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.9404. Min Act: -0.1700
Data Index: 1071746 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.9404. Min Act: -0.1700
Data Index: 8732176 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.9091. Min Act: -0.1700
Data Index: 1174813 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.8779. Min Act: -0.1700
Data Index: 3895754 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.8779. Min Act: -0.1700
Data Index: 6483337 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.8466. Min Act: -0.1700
Data Index: 8769172 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.8779. Min Act: -0.1700
Data Index: 8326961 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.8779. Min Act: -0.1700
Data Index: 8769173 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.8154. Min Act: -0.1700
Data Index: 5696214 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.8154. Min Act: -0.1700
Data Index: 7170472 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.8154. Min Act: -0.1700
Data Index: 8769175 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.7841. Min Act: -0.1700
Data Index: 8769177 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.7841. Min Act: -0.1700
Data Index: 1352211 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.7529. Min Act: -0.1700
Data Index: 547243 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.7529. Min Act: -0.1700
Data Index: 1057056 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.7529. Min Act: -0.1700
Data Index: 6974212 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0341. Min Range: -6.0341
Max Act: 5.7529. Min Act: -0.1700
Data Index: 7654992 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19