Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6199 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 30.5475. Min Range: -30.5475
Max Act: 30.5475. Min Act: -0.1700
Data Index: 7287802 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.6725. Min Act: -0.1700
Data Index: 4272906 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.7975. Min Act: -0.1700
Data Index: 7111863 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.6725. Min Act: -0.1700
Data Index: 75050 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.6725. Min Act: -0.1700
Data Index: 1221690 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.6725. Min Act: -0.1700
Data Index: 3853843 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.6725. Min Act: -0.1700
Data Index: 1717450 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.5475. Min Act: -0.1700
Data Index: 6807994 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.5475. Min Act: -0.1700
Data Index: 761346 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.4225. Min Act: -0.1700
Data Index: 4178866 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.4225. Min Act: -0.1700
Data Index: 3322229 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.4225. Min Act: -0.1700
Data Index: 2878797 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.4225. Min Act: -0.1699
Data Index: 8110495 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.2975. Min Act: -0.1700
Data Index: 6848755 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.2975. Min Act: -0.1699
Data Index: 1820807 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.2975. Min Act: -0.1700
Data Index: 5616924 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.1725. Min Act: -0.1700
Data Index: 3477760 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.1725. Min Act: -0.1700
Data Index: 5429612 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.1725. Min Act: -0.1700
Data Index: 7167883 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 30.5475. Min Range: -30.5475
Max Act: 29.1725. Min Act: -0.1700
Data Index: 4921694 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19