Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0710. Min Range: -5.0710
Max Act: 5.0710. Min Act: -0.1700
Data Index: 3827892 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.9773. Min Act: -0.1700
Data Index: 6683638 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.9460. Min Act: -0.1700
Data Index: 2170671 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.9148. Min Act: -0.1700
Data Index: 5629424 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.9148. Min Act: -0.1700
Data Index: 6959909 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.9148. Min Act: -0.1700
Data Index: 502157 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8835. Min Act: -0.1700
Data Index: 2251873 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8835. Min Act: -0.1700
Data Index: 2831592 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8835. Min Act: -0.1700
Data Index: 4962818 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8523. Min Act: -0.1700
Data Index: 4740339 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8523. Min Act: -0.1700
Data Index: 5399299 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8210. Min Act: -0.1700
Data Index: 2253022 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8210. Min Act: -0.1700
Data Index: 3398099 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8210. Min Act: -0.1700
Data Index: 8826391 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8210. Min Act: -0.1700
Data Index: 4967275 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8210. Min Act: -0.1700
Data Index: 1134713 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7898. Min Act: -0.1700
Data Index: 6914064 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7898. Min Act: -0.1700
Data Index: 3036886 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7898. Min Act: -0.1700
Data Index: 8462694 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7898. Min Act: -0.1700
Data Index: 3833356 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19