Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3300 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1537. Min Range: -8.1537
Max Act: 8.1537. Min Act: -0.1700
Data Index: 495445 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1537. Min Range: -8.1537
Max Act: 8.0912. Min Act: -0.1700
Data Index: 1021906 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1537. Min Range: -8.1537
Max Act: 8.0287. Min Act: -0.1700
Data Index: 7847572 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.9037. Min Act: -0.1700
Data Index: 35885 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.8412. Min Act: -0.1700
Data Index: 8127365 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.8412. Min Act: -0.1700
Data Index: 2014251 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.7787. Min Act: -0.1700
Data Index: 552129 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.7787. Min Act: -0.1700
Data Index: 606112 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.7162. Min Act: -0.1700
Data Index: 5937646 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.7162. Min Act: -0.1700
Data Index: 5282569 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.7162. Min Act: -0.1700
Data Index: 5064536 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.6225. Min Act: -0.1700
Data Index: 4844707 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.6537. Min Act: -0.1700
Data Index: 904940 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.5912. Min Act: -0.1700
Data Index: 5304231 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.5600. Min Act: -0.1700
Data Index: 6922942 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.5600. Min Act: -0.1700
Data Index: 289095 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.5600. Min Act: -0.1700
Data Index: 2311933 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.4975. Min Act: -0.1700
Data Index: 5344242 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.5287. Min Act: -0.1700
Data Index: 5910669 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1537. Min Range: -8.1537
Max Act: 7.5287. Min Act: -0.1700
Data Index: 5785190 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19