Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4135 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3809. Min Range: -6.3809
Max Act: 6.3809. Min Act: -0.1700
Data Index: 6377501 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3809. Min Range: -6.3809
Max Act: 6.0684. Min Act: -0.1700
Data Index: 6868489 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3809. Min Range: -6.3809
Max Act: 6.0059. Min Act: -0.1700
Data Index: 5451939 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.9434. Min Act: -0.1700
Data Index: 4338334 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.9434. Min Act: -0.1700
Data Index: 6571720 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.9434. Min Act: -0.1700
Data Index: 1333850 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.9121. Min Act: -0.1700
Data Index: 844992 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.9121. Min Act: -0.1700
Data Index: 4260450 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.8496. Min Act: -0.1700
Data Index: 5496075 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.8809. Min Act: -0.1700
Data Index: 3982302 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.8809. Min Act: -0.1700
Data Index: 6691168 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.8496. Min Act: -0.1700
Data Index: 5042784 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.8496. Min Act: -0.1700
Data Index: 8669361 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.8496. Min Act: -0.1700
Data Index: 377042 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.8184. Min Act: -0.1700
Data Index: 2286003 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.8184. Min Act: -0.1700
Data Index: 7224012 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.7871. Min Act: -0.1700
Data Index: 3968473 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.7871. Min Act: -0.1700
Data Index: 7717781 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.8184. Min Act: -0.1700
Data Index: 4165569 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3809. Min Range: -6.3809
Max Act: 5.8184. Min Act: -0.1700
Data Index: 6090911 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19