Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2842 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.8021. Min Act: -0.1700
Data Index: 2783968 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.7396. Min Act: -0.1700
Data Index: 6622649 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.6771. Min Act: -0.1700
Data Index: 2455645 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.6146. Min Act: -0.1700
Data Index: 8578792 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.5833. Min Act: -0.1700
Data Index: 813230 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.4583. Min Act: -0.1700
Data Index: 6165784 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.4583. Min Act: -0.1700
Data Index: 7282354 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.4583. Min Act: -0.1700
Data Index: 6907428 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.4271. Min Act: -0.1700
Data Index: 4039417 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.2708. Min Act: -0.1700
Data Index: 7293163 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.2708. Min Act: -0.1700
Data Index: 78744 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.1146. Min Act: -0.1700
Data Index: 4688073 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.0833. Min Act: -0.1700
Data Index: 7337256 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8021. Min Range: -7.8021
Max Act: 7.0833. Min Act: -0.1700
Data Index: 1020310 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8021. Min Range: -7.8021
Max Act: 6.9896. Min Act: -0.1700
Data Index: 1000039 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8021. Min Range: -7.8021
Max Act: 6.9896. Min Act: -0.1700
Data Index: 331965 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8021. Min Range: -7.8021
Max Act: 6.9896. Min Act: -0.1700
Data Index: 8028833 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8021. Min Range: -7.8021
Max Act: 6.9896. Min Act: -0.1700
Data Index: 8255565 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8021. Min Range: -7.8021
Max Act: 6.9896. Min Act: -0.1700
Data Index: 8760818 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8021. Min Range: -7.8021
Max Act: 6.9583. Min Act: -0.1700
Data Index: 3452894 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19