Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6398 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2340. Min Range: -5.2340
Max Act: 5.2340. Min Act: -0.1700
Data Index: 211025 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2340. Min Range: -5.2340
Max Act: 5.1090. Min Act: -0.1700
Data Index: 5515547 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2340. Min Range: -5.2340
Max Act: 5.0465. Min Act: -0.1700
Data Index: 2498946 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2340. Min Range: -5.2340
Max Act: 5.0778. Min Act: -0.1700
Data Index: 8072491 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2340. Min Range: -5.2340
Max Act: 5.0153. Min Act: -0.1700
Data Index: 2672786 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2340. Min Range: -5.2340
Max Act: 5.0153. Min Act: -0.1700
Data Index: 7999844 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9840. Min Act: -0.1700
Data Index: 6508947 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9840. Min Act: -0.1700
Data Index: 5515546 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9215. Min Act: -0.1700
Data Index: 2383375 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9528. Min Act: -0.1700
Data Index: 4832182 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9528. Min Act: -0.1700
Data Index: 2678291 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9528. Min Act: -0.1700
Data Index: 7999842 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9528. Min Act: -0.1700
Data Index: 3156190 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9215. Min Act: -0.1700
Data Index: 8731916 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9215. Min Act: -0.1700
Data Index: 7999845 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9215. Min Act: -0.1700
Data Index: 3844104 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9528. Min Act: -0.1700
Data Index: 683830 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.9528. Min Act: -0.1700
Data Index: 1007756 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.8590. Min Act: -0.1700
Data Index: 5229964 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2340. Min Range: -5.2340
Max Act: 4.8903. Min Act: -0.1700
Data Index: 2525698 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19