Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 781 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4028. Min Range: -5.4028
Max Act: 5.4028. Min Act: -0.1700
Data Index: 4344883 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4028. Min Range: -5.4028
Max Act: 5.1215. Min Act: -0.1700
Data Index: 6201527 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4028. Min Range: -5.4028
Max Act: 5.0590. Min Act: -0.1700
Data Index: 4878736 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4028. Min Range: -5.4028
Max Act: 5.0278. Min Act: -0.1700
Data Index: 3638106 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.9965. Min Act: -0.1700
Data Index: 515486 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.9965. Min Act: -0.1700
Data Index: 3312090 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.9965. Min Act: -0.1700
Data Index: 7621427 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.9340. Min Act: -0.1700
Data Index: 529896 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.8715. Min Act: -0.1700
Data Index: 590849 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.8403. Min Act: -0.1700
Data Index: 3069285 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.8715. Min Act: -0.1700
Data Index: 3408211 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 4213739 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 3918055 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 3277334 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.7778. Min Act: -0.1700
Data Index: 1431908 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.7778. Min Act: -0.1700
Data Index: 533137 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.7465. Min Act: -0.1700
Data Index: 1025007 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.7465. Min Act: -0.1700
Data Index: 1140228 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.7153. Min Act: -0.1700
Data Index: 431855 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4028. Min Range: -5.4028
Max Act: 4.7465. Min Act: -0.1700
Data Index: 3280971 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19