Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.2615. Min Act: -0.1700
Data Index: 2915270 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.1990. Min Act: -0.1700
Data Index: 50400 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.1990. Min Act: -0.1700
Data Index: 1361331 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.1365. Min Act: -0.1700
Data Index: 7469040 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.1053. Min Act: -0.1700
Data Index: 187095 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.1053. Min Act: -0.1700
Data Index: 7330089 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.0740. Min Act: -0.1700
Data Index: 380447 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.0740. Min Act: -0.1700
Data Index: 380472 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.0428. Min Act: -0.1700
Data Index: 2872709 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.0428. Min Act: -0.1700
Data Index: 5868600 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.0115. Min Act: -0.1700
Data Index: 4716750 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2615. Min Range: -5.2615
Max Act: 5.0428. Min Act: -0.1700
Data Index: 3637878 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2615. Min Range: -5.2615
Max Act: 4.9803. Min Act: -0.1700
Data Index: 1679131 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2615. Min Range: -5.2615
Max Act: 4.9490. Min Act: -0.1700
Data Index: 2225126 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2615. Min Range: -5.2615
Max Act: 4.9178. Min Act: -0.1700
Data Index: 2280 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2615. Min Range: -5.2615
Max Act: 4.9490. Min Act: -0.1700
Data Index: 4716748 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2615. Min Range: -5.2615
Max Act: 4.9178. Min Act: -0.1700
Data Index: 3549253 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2615. Min Range: -5.2615
Max Act: 4.9178. Min Act: -0.1700
Data Index: 2319767 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2615. Min Range: -5.2615
Max Act: 4.9178. Min Act: -0.1700
Data Index: 1026803 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2615. Min Range: -5.2615
Max Act: 4.9178. Min Act: -0.1700
Data Index: 7069752 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19