Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3152 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.6797. Min Act: -0.1700
Data Index: 6912033 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.5234. Min Act: -0.1700
Data Index: 5851665 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.4609. Min Act: -0.1700
Data Index: 7480805 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.3359. Min Act: -0.1700
Data Index: 6421467 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.3672. Min Act: -0.1700
Data Index: 2737938 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.3047. Min Act: -0.1700
Data Index: 4425919 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.2734. Min Act: -0.1700
Data Index: 7467589 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.2422. Min Act: -0.1700
Data Index: 3097601 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.2109. Min Act: -0.1700
Data Index: 5550489 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.2109. Min Act: -0.1700
Data Index: 1680526 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.2109. Min Act: -0.1700
Data Index: 3948317 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.1797. Min Act: -0.1700
Data Index: 5330243 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.1797. Min Act: -0.1700
Data Index: 502784 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.1484. Min Act: -0.1700
Data Index: 5754211 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.1484. Min Act: -0.1700
Data Index: 2360465 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.1172. Min Act: -0.1700
Data Index: 8083641 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.1172. Min Act: -0.1700
Data Index: 575940 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.1172. Min Act: -0.1700
Data Index: 2610702 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.1172. Min Act: -0.1700
Data Index: 1214617 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6797. Min Range: -5.6797
Max Act: 5.1172. Min Act: -0.1700
Data Index: 3006842 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19