Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1812 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.3679. Min Act: -0.1700
Data Index: 1067480 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.3366. Min Act: -0.1700
Data Index: 966494 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.3052. Min Act: -0.1700
Data Index: 4422113 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.2424. Min Act: -0.1700
Data Index: 2167280 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1952. Min Act: -0.1700
Data Index: 1364415 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1795. Min Act: -0.1700
Data Index: 1859114 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1637. Min Act: -0.1700
Data Index: 772728 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1952. Min Act: -0.1700
Data Index: 7853666 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1795. Min Act: -0.1700
Data Index: 6127214 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1637. Min Act: -0.1700
Data Index: 6402651 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1480. Min Act: -0.1700
Data Index: 1764945 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1795. Min Act: -0.1700
Data Index: 7960798 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1007. Min Act: -0.1700
Data Index: 8205552 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1480. Min Act: -0.1700
Data Index: 2966619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1322. Min Act: -0.1700
Data Index: 2232847 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1165. Min Act: -0.1700
Data Index: 4062086 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1165. Min Act: -0.1700
Data Index: 7842113 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1007. Min Act: -0.1700
Data Index: 1628461 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1007. Min Act: -0.1700
Data Index: 6529251 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3679. Min Range: -3.3679
Max Act: 3.1007. Min Act: -0.1700
Data Index: 5524179 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19