Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 482 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1149. Min Range: -7.1149
Max Act: 7.1149. Min Act: -0.1700
Data Index: 7371927 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1149. Min Range: -7.1149
Max Act: 7.0524. Min Act: -0.1700
Data Index: 2875270 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.7086. Min Act: -0.1700
Data Index: 2615974 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.7086. Min Act: -0.1700
Data Index: 1311841 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.7086. Min Act: -0.1700
Data Index: 2752917 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.6774. Min Act: -0.1700
Data Index: 2430954 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.6774. Min Act: -0.1700
Data Index: 4852552 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.6774. Min Act: -0.1699
Data Index: 3237979 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.6149. Min Act: -0.1700
Data Index: 6513780 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.6149. Min Act: -0.1700
Data Index: 4483372 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.5524. Min Act: -0.1700
Data Index: 2089939 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.5836. Min Act: -0.1700
Data Index: 2405046 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.5524. Min Act: -0.1700
Data Index: 3975604 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.5524. Min Act: -0.1700
Data Index: 8431284 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.5524. Min Act: -0.1700
Data Index: 4966700 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.5211. Min Act: -0.1700
Data Index: 6622491 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.5211. Min Act: -0.1700
Data Index: 7565127 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.5211. Min Act: -0.1700
Data Index: 1905503 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.5211. Min Act: -0.1680
Data Index: 5425569 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1149. Min Range: -7.1149
Max Act: 6.5211. Min Act: -0.1700
Data Index: 2812015 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19