Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4159 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9803. Min Act: -0.1700
Data Index: 3531610 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9803. Min Act: -0.1700
Data Index: 2433686 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9803. Min Act: -0.1700
Data Index: 3107792 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9645. Min Act: -0.1700
Data Index: 7271180 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9645. Min Act: -0.1700
Data Index: 7651241 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9645. Min Act: -0.1700
Data Index: 8275065 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9487. Min Act: -0.1700
Data Index: 181676 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9645. Min Act: -0.1700
Data Index: 3837812 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9328. Min Act: -0.1700
Data Index: 8262833 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9170. Min Act: -0.1700
Data Index: 1800666 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9328. Min Act: -0.1700
Data Index: 1812822 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9170. Min Act: -0.1700
Data Index: 6425260 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9170. Min Act: -0.1700
Data Index: 8352280 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9011. Min Act: -0.1700
Data Index: 2084226 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9011. Min Act: -0.1700
Data Index: 2058552 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.9011. Min Act: -0.1700
Data Index: 3994452 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.8694. Min Act: -0.1700
Data Index: 1112778 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.8853. Min Act: -0.1700
Data Index: 1119552 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.8853. Min Act: -0.1700
Data Index: 1258830 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9803. Min Range: -2.9803
Max Act: 2.8853. Min Act: -0.1700
Data Index: 4206041 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19