Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1193 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.2071. Min Act: -0.1700
Data Index: 6952552 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1914. Min Act: -0.1700
Data Index: 5458704 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1757. Min Act: -0.1700
Data Index: 3923875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1600. Min Act: -0.1700
Data Index: 1827193 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1600. Min Act: -0.1700
Data Index: 5370936 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1442. Min Act: -0.1700
Data Index: 2451321 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1442. Min Act: -0.1700
Data Index: 303576 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1442. Min Act: -0.1700
Data Index: 1976734 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1442. Min Act: -0.1700
Data Index: 641427 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1285. Min Act: -0.1700
Data Index: 1795151 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1285. Min Act: -0.1700
Data Index: 474588 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1285. Min Act: -0.1700
Data Index: 5927930 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1285. Min Act: -0.1700
Data Index: 6571538 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1127. Min Act: -0.1700
Data Index: 2781367 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1127. Min Act: -0.1700
Data Index: 2559304 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1127. Min Act: -0.1700
Data Index: 4918058 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0970. Min Act: -0.1700
Data Index: 1502360 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0812. Min Act: -0.1700
Data Index: 5377570 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0970. Min Act: -0.1700
Data Index: 1147820 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0970. Min Act: -0.1700
Data Index: 6174011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19