Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.1840. Min Act: -0.1700
Data Index: 6187634 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.1840. Min Act: -0.1700
Data Index: 8147708 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.1528. Min Act: -0.1700
Data Index: 1151250 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.1528. Min Act: -0.1700
Data Index: 3354576 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.0903. Min Act: -0.1700
Data Index: 4215667 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1840. Min Range: -5.1840
Max Act: 5.0590. Min Act: -0.1700
Data Index: 413347 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9965. Min Act: -0.1700
Data Index: 8294838 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9653. Min Act: -0.1700
Data Index: 5229374 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9653. Min Act: -0.1700
Data Index: 6703170 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9653. Min Act: -0.1700
Data Index: 150843 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 8103996 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9653. Min Act: -0.1700
Data Index: 49865 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 6008874 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 7627404 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9028. Min Act: -0.1700
Data Index: 7119823 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 1578482 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9340. Min Act: -0.1700
Data Index: 6269740 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9028. Min Act: -0.1700
Data Index: 4029922 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9028. Min Act: -0.1700
Data Index: 1888278 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1840. Min Range: -5.1840
Max Act: 4.9028. Min Act: -0.1700
Data Index: 6843042 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19