Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1729 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.3087. Min Act: -0.1700
Data Index: 5667438 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.3400. Min Act: -0.1700
Data Index: 7754279 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.3087. Min Act: -0.1700
Data Index: 6490517 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.3087. Min Act: -0.1700
Data Index: 813453 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.3087. Min Act: -0.1700
Data Index: 6490515 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.3087. Min Act: -0.1700
Data Index: 8473511 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.3087. Min Act: -0.1700
Data Index: 6055073 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.3087. Min Act: -0.1700
Data Index: 6994334 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.2462. Min Act: -0.1700
Data Index: 7754272 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.2462. Min Act: -0.1700
Data Index: 8698656 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.2150. Min Act: -0.1700
Data Index: 1224231 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.1837. Min Act: -0.1700
Data Index: 7848144 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.1837. Min Act: -0.1700
Data Index: 3023501 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.1837. Min Act: -0.1700
Data Index: 281061 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.1524. Min Act: -0.1700
Data Index: 8827761 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.1524. Min Act: -0.1700
Data Index: 5093376 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.1524. Min Act: -0.1700
Data Index: 139793 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.1837. Min Act: -0.1700
Data Index: 6055071 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.1524. Min Act: -0.1700
Data Index: 5353747 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3400. Min Range: -4.3400
Max Act: 4.1212. Min Act: -0.1700
Data Index: 7723025 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19