Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2210 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.2164. Min Act: -0.1700
Data Index: 6585356 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1535. Min Act: -0.1700
Data Index: 993774 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1535. Min Act: -0.1700
Data Index: 4272256 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1377. Min Act: -0.1700
Data Index: 7732640 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1377. Min Act: -0.1700
Data Index: 3231483 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1377. Min Act: -0.1700
Data Index: 6646997 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1220. Min Act: -0.1700
Data Index: 2739142 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1220. Min Act: -0.1700
Data Index: 6669749 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1220. Min Act: -0.1700
Data Index: 92203 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1062. Min Act: -0.1700
Data Index: 7518607 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1062. Min Act: -0.1700
Data Index: 2253193 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1220. Min Act: -0.1700
Data Index: 50152 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1062. Min Act: -0.1700
Data Index: 5941013 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1062. Min Act: -0.1700
Data Index: 2582345 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0905. Min Act: -0.1700
Data Index: 4345882 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1062. Min Act: -0.1700
Data Index: 3595521 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1062. Min Act: -0.1700
Data Index: 1316941 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1062. Min Act: -0.1700
Data Index: 1060285 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1220. Min Act: -0.1700
Data Index: 7264816 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1062. Min Act: -0.1700
Data Index: 4586591 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19