Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2130 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.3641. Min Act: -0.1700
Data Index: 4421308 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.2385. Min Act: -0.1700
Data Index: 4710357 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.2228. Min Act: -0.1700
Data Index: 509794 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.1913. Min Act: -0.1700
Data Index: 4710366 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.1441. Min Act: -0.1700
Data Index: 5556948 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.1126. Min Act: -0.1700
Data Index: 6130868 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.1126. Min Act: -0.1700
Data Index: 5437629 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.1126. Min Act: -0.1700
Data Index: 3428122 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.1126. Min Act: -0.1700
Data Index: 1380445 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.0968. Min Act: -0.1700
Data Index: 7686964 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.1126. Min Act: -0.1700
Data Index: 6446191 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.1126. Min Act: -0.1700
Data Index: 4333275 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.0968. Min Act: -0.1700
Data Index: 914564 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.0811. Min Act: -0.1700
Data Index: 8121509 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.0653. Min Act: -0.1700
Data Index: 8493499 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.0968. Min Act: -0.1700
Data Index: 1961070 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.0811. Min Act: -0.1700
Data Index: 1064673 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.0495. Min Act: -0.1700
Data Index: 8644183 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.0653. Min Act: -0.1700
Data Index: 6900382 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3641. Min Range: -3.3641
Max Act: 3.0811. Min Act: -0.1700
Data Index: 1708669 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19