Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2765 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4558. Min Range: -7.4558
Max Act: 7.4558. Min Act: -0.1700
Data Index: 2531433 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4558. Min Range: -7.4558
Max Act: 7.4246. Min Act: -0.1700
Data Index: 1596357 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4558. Min Range: -7.4558
Max Act: 7.2058. Min Act: -0.1700
Data Index: 3133464 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4558. Min Range: -7.4558
Max Act: 7.2058. Min Act: -0.1700
Data Index: 2293166 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4558. Min Range: -7.4558
Max Act: 7.2058. Min Act: -0.1700
Data Index: 8635375 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4558. Min Range: -7.4558
Max Act: 7.2058. Min Act: -0.1700
Data Index: 2153945 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4558. Min Range: -7.4558
Max Act: 7.1121. Min Act: -0.1700
Data Index: 904136 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4558. Min Range: -7.4558
Max Act: 7.0808. Min Act: -0.1700
Data Index: 8098988 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4558. Min Range: -7.4558
Max Act: 7.0808. Min Act: -0.1700
Data Index: 5941923 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4558. Min Range: -7.4558
Max Act: 7.0808. Min Act: -0.1700
Data Index: 5191540 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4558. Min Range: -7.4558
Max Act: 6.9871. Min Act: -0.1700
Data Index: 6128584 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4558. Min Range: -7.4558
Max Act: 6.9871. Min Act: -0.1700
Data Index: 6515955 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4558. Min Range: -7.4558
Max Act: 6.9871. Min Act: -0.1700
Data Index: 5846465 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4558. Min Range: -7.4558
Max Act: 6.9871. Min Act: -0.1700
Data Index: 369446 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4558. Min Range: -7.4558
Max Act: 6.9871. Min Act: -0.1700
Data Index: 3958985 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4558. Min Range: -7.4558
Max Act: 6.9558. Min Act: -0.1700
Data Index: 123287 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4558. Min Range: -7.4558
Max Act: 6.9558. Min Act: -0.1700
Data Index: 870615 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4558. Min Range: -7.4558
Max Act: 6.9246. Min Act: -0.1700
Data Index: 6544118 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4558. Min Range: -7.4558
Max Act: 6.9246. Min Act: -0.1700
Data Index: 3140628 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4558. Min Range: -7.4558
Max Act: 6.8933. Min Act: -0.1700
Data Index: 2998376 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19