Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3955 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2779. Min Act: -0.1694
Data Index: 3410497 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.1521. Min Act: -0.1693
Data Index: 4194186 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.0891. Min Act: -0.1695
Data Index: 4894270 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.0891. Min Act: -0.1700
Data Index: 4194185 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.0576. Min Act: -0.1687
Data Index: 4194183 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.0576. Min Act: -0.1690
Data Index: 7733210 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.0576. Min Act: -0.1685
Data Index: 3248562 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9944. Min Act: -0.1699
Data Index: 6239239 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.0576. Min Act: -0.1641
Data Index: 4783736 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.0260. Min Act: -0.1687
Data Index: 7161025 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9944. Min Act: -0.1674
Data Index: 4194757 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9944. Min Act: -0.1677
Data Index: 7764329 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9786. Min Act: -0.1697
Data Index: 2646815 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9786. Min Act: -0.1700
Data Index: 3958615 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9786. Min Act: -0.1700
Data Index: 5643004 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9786. Min Act: -0.1697
Data Index: 4569495 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9628. Min Act: -0.1700
Data Index: 7839860 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9153. Min Act: -0.1699
Data Index: 6126202 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9469. Min Act: -0.1699
Data Index: 5001803 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2779. Min Range: -3.2779
Max Act: 2.9469. Min Act: -0.1654
Data Index: 5222169 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19