Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 308 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.5891. Min Act: -0.1700
Data Index: 4966621 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.5266. Min Act: -0.1700
Data Index: 5287779 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.4328. Min Act: -0.1700
Data Index: 2776218 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.3703. Min Act: -0.1700
Data Index: 7685148 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.2766. Min Act: -0.1700
Data Index: 1061406 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.2766. Min Act: -0.1700
Data Index: 1688374 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.2766. Min Act: -0.1700
Data Index: 8677504 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.2141. Min Act: -0.1700
Data Index: 7150206 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.2453. Min Act: -0.1700
Data Index: 6192015 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.2141. Min Act: -0.1700
Data Index: 8789099 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.1828. Min Act: -0.1700
Data Index: 4946378 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.1828. Min Act: -0.1700
Data Index: 8003943 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.1203. Min Act: -0.1700
Data Index: 913789 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.1203. Min Act: -0.1700
Data Index: 2918464 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.1203. Min Act: -0.1700
Data Index: 2082410 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.1203. Min Act: -0.1700
Data Index: 1491884 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.1203. Min Act: -0.1700
Data Index: 7634012 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.0891. Min Act: -0.1700
Data Index: 4524550 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.0891. Min Act: -0.1700
Data Index: 1841989 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5891. Min Range: -6.5891
Max Act: 6.0578. Min Act: -0.1700
Data Index: 7228971 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19