Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3764 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.8884. Min Act: -0.1700
Data Index: 3598304 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.8259. Min Act: -0.1700
Data Index: 1294571 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.7634. Min Act: -0.1700
Data Index: 4346225 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.6071. Min Act: -0.1700
Data Index: 4431930 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5759. Min Act: -0.1700
Data Index: 1331848 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5759. Min Act: -0.1700
Data Index: 6557720 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.4509. Min Act: -0.1700
Data Index: 3073471 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.4509. Min Act: -0.1700
Data Index: 5990100 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.4509. Min Act: -0.1700
Data Index: 793207 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3884. Min Act: -0.1700
Data Index: 929263 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3884. Min Act: -0.1700
Data Index: 4133954 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3571. Min Act: -0.1700
Data Index: 2582080 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3571. Min Act: -0.1700
Data Index: 1178904 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3259. Min Act: -0.1700
Data Index: 1654334 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3571. Min Act: -0.1700
Data Index: 5168547 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3259. Min Act: -0.1700
Data Index: 2890784 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3259. Min Act: -0.1700
Data Index: 1724690 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3571. Min Act: -0.1700
Data Index: 501660 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3259. Min Act: -0.1700
Data Index: 4301545 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.3259. Min Act: -0.1700
Data Index: 7475644 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19