Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4973 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0218. Min Range: -4.0218
Max Act: 4.0218. Min Act: -0.1700
Data Index: 7767175 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.9905. Min Act: -0.1700
Data Index: 42919 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.9905. Min Act: -0.1700
Data Index: 6715514 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.9905. Min Act: -0.1700
Data Index: 2824832 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8811. Min Act: -0.1700
Data Index: 3269069 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8811. Min Act: -0.1700
Data Index: 6471406 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8811. Min Act: -0.1700
Data Index: 4122021 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8655. Min Act: -0.1700
Data Index: 5487878 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8655. Min Act: -0.1700
Data Index: 8761268 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8811. Min Act: -0.1700
Data Index: 6819338 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8655. Min Act: -0.1700
Data Index: 4671985 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8498. Min Act: -0.1700
Data Index: 8100928 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8186. Min Act: -0.1700
Data Index: 158714 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8342. Min Act: -0.1700
Data Index: 7629947 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.8029. Min Act: -0.1700
Data Index: 3968838 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.7873. Min Act: -0.1700
Data Index: 4702254 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.7873. Min Act: -0.1700
Data Index: 4575485 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.7404. Min Act: -0.1700
Data Index: 5959232 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.7560. Min Act: -0.1700
Data Index: 5627644 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0218. Min Range: -4.0218
Max Act: 3.7247. Min Act: -0.1700
Data Index: 1783628 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19