Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2212 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.9188. Min Act: -0.1700
Data Index: 5216819 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.9188. Min Act: -0.1700
Data Index: 3118671 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.8251. Min Act: -0.1700
Data Index: 2613154 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.7938. Min Act: -0.1700
Data Index: 3524865 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.7938. Min Act: -0.1700
Data Index: 5033448 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.7626. Min Act: -0.1700
Data Index: 7987462 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.7001. Min Act: -0.1700
Data Index: 5895599 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.7001. Min Act: -0.1700
Data Index: 5830726 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6688. Min Act: -0.1700
Data Index: 5184921 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.7001. Min Act: -0.1700
Data Index: 493050 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6376. Min Act: -0.1700
Data Index: 1334454 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6688. Min Act: -0.1700
Data Index: 4680189 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6688. Min Act: -0.1700
Data Index: 4400226 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6688. Min Act: -0.1700
Data Index: 4275357 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6688. Min Act: -0.1700
Data Index: 8060840 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6688. Min Act: -0.1700
Data Index: 1090130 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6376. Min Act: -0.1700
Data Index: 1861159 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6063. Min Act: -0.1700
Data Index: 638738 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6376. Min Act: -0.1700
Data Index: 455609 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9188. Min Range: -4.9188
Max Act: 4.6376. Min Act: -0.1700
Data Index: 4504050 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19