Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 426 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.3247. Min Act: -0.1682
Data Index: 3206839 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.3082. Min Act: -0.1645
Data Index: 3197477 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2753. Min Act: -0.1700
Data Index: 5862705 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2753. Min Act: -0.1700
Data Index: 5132992 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2423. Min Act: -0.1679
Data Index: 633135 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2423. Min Act: -0.1671
Data Index: 6367690 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2423. Min Act: -0.1700
Data Index: 7585310 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2588. Min Act: -0.1687
Data Index: 5606546 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2423. Min Act: -0.1699
Data Index: 8255092 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2423. Min Act: -0.1696
Data Index: 185005 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2257. Min Act: -0.1699
Data Index: 3525950 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2257. Min Act: -0.1699
Data Index: 1580298 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2257. Min Act: -0.1700
Data Index: 1912521 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2257. Min Act: -0.1653
Data Index: 411928 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2257. Min Act: -0.1700
Data Index: 4574219 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2257. Min Act: -0.1696
Data Index: 5669678 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.2092. Min Act: -0.1616
Data Index: 1997647 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.1926. Min Act: -0.1637
Data Index: 414894 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.1926. Min Act: -0.1700
Data Index: 212472 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3247. Min Range: -2.3247
Max Act: 2.1760. Min Act: -0.1700
Data Index: 445461 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19