Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.1010. Min Act: -0.1700
Data Index: 3353254 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0697. Min Act: -0.1700
Data Index: 5087085 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0697. Min Act: -0.1700
Data Index: 6657946 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0697. Min Act: -0.1700
Data Index: 3331280 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0697. Min Act: -0.1700
Data Index: 5720599 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0385. Min Act: -0.1700
Data Index: 1734443 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0385. Min Act: -0.1700
Data Index: 8018083 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0385. Min Act: -0.1700
Data Index: 6371645 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1010. Min Range: -4.1010
Max Act: 3.9759. Min Act: -0.1699
Data Index: 2273389 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 7541210 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 2946859 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1010. Min Range: -4.1010
Max Act: 3.9759. Min Act: -0.1700
Data Index: 6562768 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 2770972 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1010. Min Range: -4.1010
Max Act: 3.9759. Min Act: -0.1700
Data Index: 5095215 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 4631149 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 4093083 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1010. Min Range: -4.1010
Max Act: 3.9759. Min Act: -0.1700
Data Index: 611655 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1010. Min Range: -4.1010
Max Act: 3.9759. Min Act: -0.1700
Data Index: 3028857 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1010. Min Range: -4.1010
Max Act: 3.9447. Min Act: -0.1700
Data Index: 3223935 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1010. Min Range: -4.1010
Max Act: 3.9759. Min Act: -0.1700
Data Index: 2111442 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19