Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1060 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.1314. Min Act: -0.1700
Data Index: 2559375 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.1314. Min Act: -0.1700
Data Index: 3033969 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.1314. Min Act: -0.1700
Data Index: 3654987 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0683. Min Act: -0.1700
Data Index: 1163180 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0683. Min Act: -0.1700
Data Index: 3654988 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0368. Min Act: -0.1700
Data Index: 7314034 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0368. Min Act: -0.1700
Data Index: 3867515 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0368. Min Act: -0.1700
Data Index: 1163177 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0368. Min Act: -0.1700
Data Index: 2085042 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0368. Min Act: -0.1700
Data Index: 7143629 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0368. Min Act: -0.1700
Data Index: 8824967 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0052. Min Act: -0.1700
Data Index: 2640278 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0052. Min Act: -0.1700
Data Index: 6961889 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0052. Min Act: -0.1700
Data Index: 8528181 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0052. Min Act: -0.1700
Data Index: 8241362 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0052. Min Act: -0.1700
Data Index: 7635744 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0052. Min Act: -0.1700
Data Index: 8529698 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1314. Min Range: -3.1314
Max Act: 3.0052. Min Act: -0.1700
Data Index: 883208 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1314. Min Range: -3.1314
Max Act: 2.9735. Min Act: -0.1700
Data Index: 6244013 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1314. Min Range: -3.1314
Max Act: 2.9894. Min Act: -0.1700
Data Index: 5194532 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19