Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4173 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7160. Min Range: -10.7160
Max Act: 10.7160. Min Act: -0.1700
Data Index: 5890523 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7160. Min Range: -10.7160
Max Act: 10.0910. Min Act: -0.1700
Data Index: 353521 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7160. Min Range: -10.7160
Max Act: 10.0285. Min Act: -0.1700
Data Index: 5836140 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.9660. Min Act: -0.1700
Data Index: 2230917 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.9035. Min Act: -0.1700
Data Index: 3436628 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.9035. Min Act: -0.1700
Data Index: 1515032 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.8410. Min Act: -0.1700
Data Index: 7728748 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.7160. Min Act: -0.1700
Data Index: 7757908 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.7160. Min Act: -0.1700
Data Index: 6075277 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.7160. Min Act: -0.1700
Data Index: 6524953 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.7160. Min Act: -0.1700
Data Index: 2372500 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.7160. Min Act: -0.1700
Data Index: 5881583 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.6535. Min Act: -0.1700
Data Index: 4757957 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.7160. Min Act: -0.1700
Data Index: 8615085 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.7160. Min Act: -0.1700
Data Index: 2644460 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.7160. Min Act: -0.1700
Data Index: 1381729 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.7160. Min Act: -0.1700
Data Index: 870627 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.6535. Min Act: -0.1700
Data Index: 6755045 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.5910. Min Act: -0.1700
Data Index: 3328661 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7160. Min Range: -10.7160
Max Act: 9.6535. Min Act: -0.1700
Data Index: 5841242 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19