Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.9558. Min Act: -0.1700
Data Index: 5478749 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.8924. Min Act: -0.1700
Data Index: 594861 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.8765. Min Act: -0.1700
Data Index: 6663499 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.8130. Min Act: -0.1700
Data Index: 1753325 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7811. Min Act: -0.1700
Data Index: 752335 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7811. Min Act: -0.1700
Data Index: 1129646 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7652. Min Act: -0.1700
Data Index: 5013290 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7652. Min Act: -0.1700
Data Index: 983234 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7492. Min Act: -0.1700
Data Index: 8036032 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7652. Min Act: -0.1700
Data Index: 2692745 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7172. Min Act: -0.1700
Data Index: 4156557 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7013. Min Act: -0.1700
Data Index: 6947994 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.6852. Min Act: -0.1700
Data Index: 4210380 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7013. Min Act: -0.1700
Data Index: 7917488 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7013. Min Act: -0.1700
Data Index: 7717977 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.7013. Min Act: -0.1700
Data Index: 2235804 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.6852. Min Act: -0.1700
Data Index: 7205107 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.6692. Min Act: -0.1700
Data Index: 7592961 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.6692. Min Act: -0.1700
Data Index: 6673055 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9558. Min Range: -2.9558
Max Act: 2.6692. Min Act: -0.1700
Data Index: 509008 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19