Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4116 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.2430. Min Act: -0.1700
Data Index: 119074 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.1801. Min Act: -0.1700
Data Index: 6803141 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.1643. Min Act: -0.1700
Data Index: 6803146 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.1486. Min Act: -0.1700
Data Index: 4383114 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.1329. Min Act: -0.1700
Data Index: 4251598 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.1329. Min Act: -0.1700
Data Index: 7720785 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.1013. Min Act: -0.1700
Data Index: 7125193 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.1171. Min Act: -0.1700
Data Index: 7067678 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.1013. Min Act: -0.1700
Data Index: 4819737 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0856. Min Act: -0.1700
Data Index: 2404378 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0856. Min Act: -0.1700
Data Index: 6064599 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0856. Min Act: -0.1700
Data Index: 3420403 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0698. Min Act: -0.1700
Data Index: 2926219 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0540. Min Act: -0.1700
Data Index: 7034194 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0540. Min Act: -0.1700
Data Index: 2876090 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0540. Min Act: -0.1700
Data Index: 3558940 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0540. Min Act: -0.1700
Data Index: 1901419 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0383. Min Act: -0.1700
Data Index: 914417 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0383. Min Act: -0.1700
Data Index: 5979494 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0383. Min Act: -0.1700
Data Index: 3035494 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19