Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3940 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.9425. Min Act: -0.1700
Data Index: 670226 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.9112. Min Act: -0.1699
Data Index: 1792665 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.9112. Min Act: -0.1700
Data Index: 4176919 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.8800. Min Act: -0.1700
Data Index: 4349476 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.8800. Min Act: -0.1700
Data Index: 5522052 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.8800. Min Act: -0.1700
Data Index: 1415844 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.8175. Min Act: -0.1700
Data Index: 7673379 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7862. Min Act: -0.1700
Data Index: 1876050 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7862. Min Act: -0.1700
Data Index: 4331344 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7862. Min Act: -0.1699
Data Index: 2522706 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7862. Min Act: -0.1699
Data Index: 8163391 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7862. Min Act: -0.1700
Data Index: 5196298 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7862. Min Act: -0.1700
Data Index: 2906924 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7862. Min Act: -0.1700
Data Index: 7339444 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7550. Min Act: -0.1700
Data Index: 1876051 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7550. Min Act: -0.1700
Data Index: 2522704 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7550. Min Act: -0.1700
Data Index: 3688242 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7237. Min Act: -0.1700
Data Index: 8361190 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7550. Min Act: -0.1696
Data Index: 2169945 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.6925. Min Act: -0.1700
Data Index: 4919361 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19