Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2962 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.7688. Min Act: -0.1700
Data Index: 7754893 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.7063. Min Act: -0.1700
Data Index: 612862 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.6750. Min Act: -0.1700
Data Index: 7389605 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.6125. Min Act: -0.1700
Data Index: 3832279 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.6125. Min Act: -0.1700
Data Index: 245939 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.5813. Min Act: -0.1700
Data Index: 245943 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.5188. Min Act: -0.1700
Data Index: 7570042 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.5500. Min Act: -0.1700
Data Index: 7020530 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.5500. Min Act: -0.1700
Data Index: 3060999 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.5188. Min Act: -0.1700
Data Index: 2287031 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.4875. Min Act: -0.1700
Data Index: 4949173 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.5500. Min Act: -0.1700
Data Index: 3553895 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.4875. Min Act: -0.1700
Data Index: 3612975 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.4875. Min Act: -0.1700
Data Index: 3576958 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.5188. Min Act: -0.1700
Data Index: 1600218 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.4875. Min Act: -0.1700
Data Index: 4261332 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.4875. Min Act: -0.1700
Data Index: 3529570 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.4875. Min Act: -0.1700
Data Index: 7983830 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.4563. Min Act: -0.1700
Data Index: 6864867 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7688. Min Range: -5.7688
Max Act: 5.4563. Min Act: -0.1700
Data Index: 1449029 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19