Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2357 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.3867. Min Act: -0.1700
Data Index: 5004837 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.3242. Min Act: -0.1700
Data Index: 4679667 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.3242. Min Act: -0.1700
Data Index: 1446616 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.3554. Min Act: -0.1700
Data Index: 4176255 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.1367. Min Act: -0.1700
Data Index: 126861 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.1367. Min Act: -0.1700
Data Index: 6946146 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.1367. Min Act: -0.1700
Data Index: 2723632 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.1054. Min Act: -0.1700
Data Index: 7732808 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.1054. Min Act: -0.1700
Data Index: 6452977 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.1054. Min Act: -0.1700
Data Index: 1271414 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.0742. Min Act: -0.1700
Data Index: 7749446 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.0429. Min Act: -0.1700
Data Index: 6764901 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.0742. Min Act: -0.1700
Data Index: 2352673 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3867. Min Range: -6.3867
Max Act: 6.0429. Min Act: -0.1700
Data Index: 239211 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3867. Min Range: -6.3867
Max Act: 5.9804. Min Act: -0.1700
Data Index: 1747713 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3867. Min Range: -6.3867
Max Act: 5.9804. Min Act: -0.1700
Data Index: 7521760 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3867. Min Range: -6.3867
Max Act: 5.9804. Min Act: -0.1700
Data Index: 6041250 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3867. Min Range: -6.3867
Max Act: 5.9492. Min Act: -0.1700
Data Index: 3526727 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3867. Min Range: -6.3867
Max Act: 5.9492. Min Act: -0.1700
Data Index: 154560 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3867. Min Range: -6.3867
Max Act: 5.9179. Min Act: -0.1700
Data Index: 5427912 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19