Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 826 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9891. Min Range: -10.9891
Max Act: 10.9891. Min Act: -0.1700
Data Index: 5201223 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9891. Min Range: -10.9891
Max Act: 10.8016. Min Act: -0.1700
Data Index: 5103970 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9891. Min Range: -10.9891
Max Act: 10.5516. Min Act: -0.1700
Data Index: 2481223 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9891. Min Range: -10.9891
Max Act: 10.5516. Min Act: -0.1700
Data Index: 4869384 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9891. Min Range: -10.9891
Max Act: 10.4891. Min Act: -0.1700
Data Index: 5377372 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9891. Min Range: -10.9891
Max Act: 10.2391. Min Act: -0.1700
Data Index: 8162765 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9891. Min Range: -10.9891
Max Act: 10.1766. Min Act: -0.1700
Data Index: 46810 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9891. Min Range: -10.9891
Max Act: 10.1766. Min Act: -0.1700
Data Index: 5995251 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9891. Min Range: -10.9891
Max Act: 10.1141. Min Act: -0.1700
Data Index: 4715718 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9891. Min Range: -10.9891
Max Act: 10.0516. Min Act: -0.1700
Data Index: 3757475 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9891. Min Range: -10.9891
Max Act: 9.9891. Min Act: -0.1700
Data Index: 4055037 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9891. Min Range: -10.9891
Max Act: 9.9891. Min Act: -0.1700
Data Index: 6498941 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9891. Min Range: -10.9891
Max Act: 9.9891. Min Act: -0.1700
Data Index: 431419 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9891. Min Range: -10.9891
Max Act: 9.9891. Min Act: -0.1700
Data Index: 6030045 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9891. Min Range: -10.9891
Max Act: 9.9266. Min Act: -0.1700
Data Index: 6038607 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9891. Min Range: -10.9891
Max Act: 9.8641. Min Act: -0.1700
Data Index: 2957251 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9891. Min Range: -10.9891
Max Act: 9.8016. Min Act: -0.1700
Data Index: 3109405 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9891. Min Range: -10.9891
Max Act: 9.6766. Min Act: -0.1700
Data Index: 4150502 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9891. Min Range: -10.9891
Max Act: 9.7391. Min Act: -0.1700
Data Index: 5326364 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9891. Min Range: -10.9891
Max Act: 9.7391. Min Act: -0.1700
Data Index: 186389 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19