Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4547 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.4783. Min Act: -0.1700
Data Index: 3449995 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.4158. Min Act: -0.1700
Data Index: 3018798 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.1658. Min Act: -0.1700
Data Index: 441077 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.1346. Min Act: -0.1700
Data Index: 1996657 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.1346. Min Act: -0.1700
Data Index: 3449993 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.1346. Min Act: -0.1700
Data Index: 8148763 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.1033. Min Act: -0.1700
Data Index: 5631209 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.0721. Min Act: -0.1700
Data Index: 7960241 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.0721. Min Act: -0.1700
Data Index: 5708079 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.0721. Min Act: -0.1700
Data Index: 2016938 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.0408. Min Act: -0.1700
Data Index: 5625463 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.0408. Min Act: -0.1700
Data Index: 6060338 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.0096. Min Act: -0.1700
Data Index: 3517832 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4783. Min Range: -5.4783
Max Act: 5.0096. Min Act: -0.1700
Data Index: 3430969 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4783. Min Range: -5.4783
Max Act: 4.9783. Min Act: -0.1700
Data Index: 3112672 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4783. Min Range: -5.4783
Max Act: 4.9783. Min Act: -0.1700
Data Index: 8578964 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4783. Min Range: -5.4783
Max Act: 4.9783. Min Act: -0.1700
Data Index: 3245401 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4783. Min Range: -5.4783
Max Act: 4.9783. Min Act: -0.1700
Data Index: 7863564 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4783. Min Range: -5.4783
Max Act: 4.9783. Min Act: -0.1700
Data Index: 1937198 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4783. Min Range: -5.4783
Max Act: 4.9471. Min Act: -0.1700
Data Index: 6677929 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19