Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 520 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.4653. Min Act: -0.1700
Data Index: 6093155 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.4340. Min Act: -0.1700
Data Index: 406146 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.3715. Min Act: -0.1700
Data Index: 8625656 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.3403. Min Act: -0.1700
Data Index: 3384055 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.3403. Min Act: -0.1700
Data Index: 2261434 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.2778. Min Act: -0.1700
Data Index: 5498451 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.2778. Min Act: -0.1700
Data Index: 2813682 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.1840. Min Act: -0.1700
Data Index: 4680258 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.2153. Min Act: -0.1700
Data Index: 7439479 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.2153. Min Act: -0.1700
Data Index: 7748206 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.1840. Min Act: -0.1700
Data Index: 6666017 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.1528. Min Act: -0.1700
Data Index: 3560325 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.1528. Min Act: -0.1700
Data Index: 4193253 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.1215. Min Act: -0.1700
Data Index: 1666649 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.1215. Min Act: -0.1700
Data Index: 7366061 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.0903. Min Act: -0.1700
Data Index: 5774366 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.0590. Min Act: -0.1700
Data Index: 1256262 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.0590. Min Act: -0.1700
Data Index: 1619240 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.1215. Min Act: -0.1700
Data Index: 5046707 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4653. Min Range: -6.4653
Max Act: 6.0903. Min Act: -0.1700
Data Index: 3136298 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19