Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1838. Min Range: -8.1838
Max Act: 8.1838. Min Act: -0.1700
Data Index: 689556 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.9338. Min Act: -0.1700
Data Index: 2762955 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.8401. Min Act: -0.1700
Data Index: 2224535 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.8401. Min Act: -0.1698
Data Index: 6936860 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.7776. Min Act: -0.1700
Data Index: 5416628 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.8088. Min Act: -0.1700
Data Index: 4151233 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.7463. Min Act: -0.1700
Data Index: 5585994 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.7776. Min Act: -0.1700
Data Index: 4255754 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.7776. Min Act: -0.1700
Data Index: 3631774 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.7151. Min Act: -0.1700
Data Index: 4792791 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.6838. Min Act: -0.1700
Data Index: 2568208 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.5901. Min Act: -0.1700
Data Index: 7718010 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.5901. Min Act: -0.1700
Data Index: 3294656 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.5588. Min Act: -0.1700
Data Index: 4450081 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.5588. Min Act: -0.1700
Data Index: 1817925 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.4651. Min Act: -0.1700
Data Index: 1724234 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.4338. Min Act: -0.1700
Data Index: 2916662 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.4963. Min Act: -0.1700
Data Index: 1515844 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.4963. Min Act: -0.1700
Data Index: 5936790 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1838. Min Range: -8.1838
Max Act: 7.4651. Min Act: -0.1700
Data Index: 1330931 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19