Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 663 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2843. Min Range: -7.2843
Max Act: 7.2843. Min Act: -0.1700
Data Index: 7571206 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.9718. Min Act: -0.1700
Data Index: 7990218 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.9718. Min Act: -0.1700
Data Index: 7512030 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.8468. Min Act: -0.1700
Data Index: 7521355 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.8468. Min Act: -0.1700
Data Index: 1062107 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.7531. Min Act: -0.1700
Data Index: 1967182 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.6593. Min Act: -0.1700
Data Index: 4395891 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.6593. Min Act: -0.1700
Data Index: 8072237 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.5968. Min Act: -0.1700
Data Index: 6905860 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.6593. Min Act: -0.1700
Data Index: 1382865 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.5968. Min Act: -0.1700
Data Index: 1349444 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.5656. Min Act: -0.1700
Data Index: 1571211 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.5656. Min Act: -0.1700
Data Index: 7499303 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.5343. Min Act: -0.1700
Data Index: 8445687 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.5031. Min Act: -0.1700
Data Index: 5930260 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.4406. Min Act: -0.1700
Data Index: 3815275 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.4093. Min Act: -0.1700
Data Index: 7602696 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.4093. Min Act: -0.1700
Data Index: 8129083 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.3781. Min Act: -0.1700
Data Index: 2557448 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2843. Min Range: -7.2843
Max Act: 6.3781. Min Act: -0.1700
Data Index: 5210104 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19