Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 950 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5787. Min Range: -6.5787
Max Act: 6.5787. Min Act: -0.1700
Data Index: 8321073 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5787. Min Range: -6.5787
Max Act: 6.1725. Min Act: -0.1700
Data Index: 6549992 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5787. Min Range: -6.5787
Max Act: 6.1100. Min Act: -0.1700
Data Index: 1590763 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5787. Min Range: -6.5787
Max Act: 6.0475. Min Act: -0.1700
Data Index: 3455479 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.9225. Min Act: -0.1700
Data Index: 4689739 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.8912. Min Act: -0.1700
Data Index: 6841765 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.8600. Min Act: -0.1700
Data Index: 4487485 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.8600. Min Act: -0.1700
Data Index: 1693458 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.8287. Min Act: -0.1700
Data Index: 2585056 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.8287. Min Act: -0.1700
Data Index: 1913281 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.7975. Min Act: -0.1700
Data Index: 6668869 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.8287. Min Act: -0.1700
Data Index: 5596367 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.7975. Min Act: -0.1700
Data Index: 7219801 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.7975. Min Act: -0.1700
Data Index: 6564080 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.7350. Min Act: -0.1700
Data Index: 4505088 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.7662. Min Act: -0.1700
Data Index: 7363031 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.7662. Min Act: -0.1700
Data Index: 5610566 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.7350. Min Act: -0.1700
Data Index: 642541 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.7350. Min Act: -0.1700
Data Index: 7087086 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5787. Min Range: -6.5787
Max Act: 5.7350. Min Act: -0.1700
Data Index: 7650067 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19