Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5156 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.9058. Min Act: -0.1700
Data Index: 4622244 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.9058. Min Act: -0.1700
Data Index: 2903082 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.8433. Min Act: -0.1700
Data Index: 4006911 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.7808. Min Act: -0.1700
Data Index: 5403365 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.7808. Min Act: -0.1700
Data Index: 7745100 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.7808. Min Act: -0.1700
Data Index: 7663494 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.7496. Min Act: -0.1700
Data Index: 6449239 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.7496. Min Act: -0.1700
Data Index: 7686602 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.7183. Min Act: -0.1700
Data Index: 6001397 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.7183. Min Act: -0.1700
Data Index: 390605 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.6871. Min Act: -0.1700
Data Index: 2830577 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.6871. Min Act: -0.1700
Data Index: 242987 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.6558. Min Act: -0.1700
Data Index: 563689 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.6871. Min Act: -0.1700
Data Index: 8238073 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.6558. Min Act: -0.1700
Data Index: 6752897 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.6558. Min Act: -0.1700
Data Index: 563699 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.6558. Min Act: -0.1700
Data Index: 3456100 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.6558. Min Act: -0.1700
Data Index: 818014 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.6558. Min Act: -0.1700
Data Index: 1650019 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9058. Min Range: -5.9058
Max Act: 5.6558. Min Act: -0.1700
Data Index: 8032187 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19