Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.4097. Min Act: -0.1700
Data Index: 128235 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.4097. Min Act: -0.1700
Data Index: 1923945 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.3784. Min Act: -0.1180
Data Index: 1320783 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.3159. Min Act: -0.1700
Data Index: 3912762 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.2534. Min Act: -0.1700
Data Index: 8620266 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.2534. Min Act: -0.1700
Data Index: 3574686 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.2534. Min Act: -0.1700
Data Index: 8330878 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.2222. Min Act: -0.1700
Data Index: 547222 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.2222. Min Act: -0.1666
Data Index: 6263117 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.1909. Min Act: -0.1700
Data Index: 2334028 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.1909. Min Act: -0.1700
Data Index: 3548440 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.1909. Min Act: -0.1700
Data Index: 3259157 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.1909. Min Act: -0.1674
Data Index: 6263115 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.1284. Min Act: -0.1700
Data Index: 7635860 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.1284. Min Act: -0.1700
Data Index: 3950479 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.1284. Min Act: -0.1690
Data Index: 5046392 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.1284. Min Act: -0.0773
Data Index: 7038149 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.0972. Min Act: -0.1700
Data Index: 3520265 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.1597. Min Act: -0.1700
Data Index: 6161610 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4097. Min Range: -5.4097
Max Act: 5.1284. Min Act: -0.1689
Data Index: 6263130 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19