Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4931 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.2651. Min Act: -0.1700
Data Index: 2942950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.2651. Min Act: -0.1700
Data Index: 6141116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.2651. Min Act: -0.1700
Data Index: 8491735 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.2651. Min Act: -0.1700
Data Index: 5771598 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.1714. Min Act: -0.1700
Data Index: 4210448 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.1401. Min Act: -0.1700
Data Index: 7315518 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.1401. Min Act: -0.1700
Data Index: 3437766 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.1089. Min Act: -0.1700
Data Index: 80474 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.1089. Min Act: -0.1700
Data Index: 6164020 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.1401. Min Act: -0.1700
Data Index: 550926 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.1089. Min Act: -0.1700
Data Index: 1043393 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.0776. Min Act: -0.1700
Data Index: 1016213 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.0776. Min Act: -0.1700
Data Index: 4683605 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.0776. Min Act: -0.1700
Data Index: 5405297 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.0776. Min Act: -0.1700
Data Index: 431455 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.0463. Min Act: -0.1700
Data Index: 7857688 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.0151. Min Act: -0.1700
Data Index: 5047987 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2651. Min Range: -4.2651
Max Act: 4.0151. Min Act: -0.1700
Data Index: 7238960 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2651. Min Range: -4.2651
Max Act: 3.9838. Min Act: -0.1700
Data Index: 3194552 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2651. Min Range: -4.2651
Max Act: 3.9838. Min Act: -0.1700
Data Index: 6291454 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19